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

    Neuronpedia

    INDEX
    Explanations

    rules and commerce

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ней
    0.75
    лей
    0.48
    вей
    0.47
     Ney
    0.46
    рей
    0.42
     Hey
    0.41
    тей
    0.41
     Begin
    0.40
     Ley
    0.40
     distributing
    0.39
    POSITIVE LOGITS
    .$.
    0.51
    .$,
    0.51
    .$;
    0.50
    }($
    0.46
    нее
    0.45
    жнее
    0.45
    .$\
    0.45
    }^{
    0.44
    .$
    0.43
    }-\
    0.42
    Act Density 0.000%

    No Known Activations