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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Defaults
    -0.07
    �게
    -0.06
    _elt
    -0.06
     Our
    -0.06
    .ff
    -0.06
     Ник
    -0.06
     Bond
    -0.06
    чис
    -0.05
     Clothes
    -0.05
     Weg
    -0.05
    POSITIVE LOGITS
     sebe
    0.07
    ząd
    0.06
    onet
    0.06
     nimi
    0.06
     Petr
    0.06
    WillAppear
    0.06
     sprink
    0.06
    (SELECT
    0.06
    osti
    0.06
    çu
    0.06
    Act Density 0.285%

    No Known Activations