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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Ta
    -0.08
     Duy
    -0.07
     Isa
    -0.07
     Reds
    -0.07
    _VISIBLE
    -0.07
     FK
    -0.06
    eca
    -0.06
     prio
    -0.06
    substr
    -0.06
    adata
    -0.06
    POSITIVE LOGITS
    .isFile
    0.06
    _reduction
    0.06
    mî
    0.06
     (;
    0.06
     ^{°}
    0.06
    原来
    0.06
     (↵↵
    0.06
    visející
    0.06
    .Dispatcher
    0.06
     PRE
    0.05
    Act Density 0.170%

    No Known Activations