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

    Neuronpedia

    INDEX
    Explanations

    est

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	short
    -0.07
     getModel
    -0.07
     nv
    -0.06
    -U
    -0.06
    icare
    -0.06
    .general
    -0.06
    agine
    -0.06
    L
    -0.06
    يه
    -0.06
    ну
    -0.06
    POSITIVE LOGITS
     Liste
    0.07
    _estado
    0.07
     diverse
    0.07
    _tok
    0.06
     Cougar
    0.06
     Ком
    0.06
     같다
    0.06
     [#
    0.06
      
    0.06
    ellow
    0.06
    Act Density 0.022%

    No Known Activations