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

    Neuronpedia

    INDEX
    Explanations

    hyphenated or punctuated phrases that indicate connections between different pieces of information

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

    roles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    -0.46
     …
    -0.43
    ……
    -0.40
     ……
    -0.38
     solcher
    -0.38
     appunto
    -0.38
     solches
    -0.37
     other
    -0.37
     strip
    -0.36
    yordu
    -0.35
    POSITIVE LOGITS
    FunctionFlags
    0.55
    otheby
    0.54
    Former
    0.54
    Members
    0.54
    Governor
    0.53
    Patients
    0.52
     Patients
    0.52
    Students
    0.52
    Secretary
    0.52
    expandindo
    0.52
    Act Density 0.005%

    No Known Activations