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

    Neuronpedia

    INDEX
    Explanations

    instances of self-affirmation or expressions of individuality

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

    Punctuation marks followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    legal entities or courts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.54
    SourceChecksum
    -0.40
    enderror
    -0.38
    VPS
    -0.37
    enumi
    -0.37
    GCM
    -0.37
    ſt
    -0.36
    (#
    -0.35
     themselves
    -0.35
    TFT
    -0.34
    POSITIVE LOGITS
     badan
    0.47
    bey
    0.46
     IBRARY
    0.46
    Aiheesta
    0.46
     nobody
    0.45
    richTextPanel
    0.45
    nobody
    0.45
     dammit
    0.45
    ⟬
    0.45
    ashian
    0.44
    Act Density 0.441%

    No Known Activations