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

    Neuronpedia

    INDEX
    Explanations

    Repeated non-alphanumeric characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TRNS
    -0.07
     Accountability
    -0.07
    azing
    -0.07
    heroes
    -0.07
    ε
    -0.06
    _ctr
    -0.06
     Representation
    -0.06
    gii
    -0.06
    .assets
    -0.06
    _database
    -0.06
    POSITIVE LOGITS
     Lau
    0.07
     onclick
    0.06
     minlength
    0.06
     sneak
    0.06
     exception
    0.06
    ラ
    0.06
    ьют
    0.06
    \",↵
    0.06
     Kremlin
    0.06
    ие
    0.06
    Act Density 0.026%

    No Known Activations