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

    Neuronpedia

    INDEX
    Explanations

    T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _functions
    -0.07
     الرح
    -0.06
     دن
    -0.06
    244
    -0.06
    Criterion
    -0.06
    руч
    -0.06
    -inline
    -0.06
    .getInput
    -0.06
    朗
    -0.06
    อส
    -0.06
    POSITIVE LOGITS
     completeness
    0.08
     красив
    0.07
    _/
    0.06
     нак
    0.06
    らし
    0.06
    .modal
    0.06
    */
↵
    0.06
    เกษ
    0.06
    험
    0.06
    afil
    0.06
    Act Density 0.001%

    No Known Activations