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

    Neuronpedia

    INDEX
    Explanations

    assembly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prefers
    -0.07
    �
    -0.06
     gad
    -0.06
    plist
    -0.06
    ाहत
    -0.06
     diversion
    -0.06
     createAction
    -0.06
    scopes
    -0.06
     얼굴
    -0.06
    contr
    -0.06
    POSITIVE LOGITS
    .Logic
    0.07
    hack
    0.06
     poids
    0.06
     Souls
    0.06
     рекоменда
    0.06
    gebn
    0.06
     Μη
    0.06
    ％
    0.06
     contacting
    0.06
    ZONE
    0.06
    Act Density 0.044%

    No Known Activations