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

    Neuronpedia

    INDEX
    Explanations

    proceed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     naš
    -0.07
    ','
    -0.06
     взя
    -0.06
    евые
    -0.06
     воды
    -0.06
    もの
    -0.06
    -'
    -0.06
     стены
    -0.06
     tonic
    -0.06
     Repository
    -0.06
    POSITIVE LOGITS
     stra
    0.07
    Segue
    0.06
     squash
    0.06
    lete
    0.06
    .GetCurrentMethod
    0.06
     Loads
    0.06
    aq
    0.06
    �
    0.06
     товари
    0.06
     segue
    0.06
    Act Density 0.017%

    No Known Activations