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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ับน
    -0.06
    fter
    -0.06
    SGlobal
    -0.06
    _HALF
    -0.06
     aver
    -0.06
    _workspace
    -0.06
    atement
    -0.06
     点
    -0.06
     TAS
    -0.06
    POSITIVE LOGITS
     Walker
    0.08
     activity
    0.06
    _inst
    0.06
     Wiring
    0.06
     pull
    0.06
     entertain
    0.06
    огод
    0.06
     січня
    0.06
     varsa
    0.06
    ób
    0.06
    Act Density 0.102%

    No Known Activations