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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Grace
    -0.07
     Empire
    -0.06
     paren
    -0.06
    lesai
    -0.06
     Arms
    -0.06
     McD
    -0.06
    ありがとうござ
    -0.06
     perso
    -0.06
     součástí
    -0.06
    "F
    -0.06
    POSITIVE LOGITS
    abit
    0.06
    _collect
    0.06
     лекар
    0.06
    ochond
    0.06
    μί
    0.06
    _security
    0.06
     Griff
    0.06
     je
    0.06
     Sheikh
    0.06
     Checked
    0.06
    Act Density 0.018%

    No Known Activations