Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and relationships within physics, particularly relating to fields and particle behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Positive/negative signs, same/opposite

    np_acts-logits-general · gemini-2.0-flash

    same or opposite signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    שרה
    -0.49
    \{\\
    -0.48
    gelöst
    -0.45
     thinly
    -0.45
    rensa
    -0.44
    kfree
    -0.41
    tainen
    -0.41
    Blur
    -0.40
     gegeben
    -0.40
    rxjs
    -0.40
    POSITIVE LOGITS
     sign
    1.61
     negative
    1.47
     positive
    1.44
     Positive
    1.34
    negative
    1.33
     Sign
    1.31
    sign
    1.31
     Negative
    1.31
     POSITIVE
    1.29
     signs
    1.29
    Act Density 1.085%

    No Known Activations