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

    Neuronpedia

    INDEX
    Explanations

    preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rs
    -0.08
     dicho
    -0.07
    thresh
    -0.07
    аша
    -0.07
    viewer
    -0.07
     fk
    -0.06
    ,char
    -0.06
    ZF
    -0.06
     pessoa
    -0.06
    _Show
    -0.06
    POSITIVE LOGITS
    ンデ
    0.07
     perpetrated
    0.07
    	RE
    0.07
     ordinary
    0.06
     때문에
    0.06
    vector
    0.06
     unab
    0.06
    GRAPH
    0.06
    _executor
    0.06
    _dataframe
    0.06
    Act Density 0.002%

    No Known Activations