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

    Neuronpedia

    INDEX
    Explanations

    surveys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resposta
    -0.07
    wifi
    -0.06
    руется
    -0.06
     logistic
    -0.06
     newIndex
    -0.06
    _index
    -0.06
    _dataset
    -0.06
    _MOD
    -0.06
    官方
    -0.06
    ede
    -0.06
    POSITIVE LOGITS
     entire
    0.07
    Beautiful
    0.07
     Traditional
    0.07
     envelop
    0.06
    	login
    0.06
    .month
    0.06
     Latinos
    0.06
    역
    0.06
    NullOr
    0.06
    По
    0.06
    Act Density 0.167%

    No Known Activations