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

    Neuronpedia

    INDEX
    Explanations

    Code/Image references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (/*
    -0.08
     Everything
    -0.07
     masturb
    -0.06
    清
    -0.06
    ._
    -0.06
    _MAY
    -0.06
     brow
    -0.06
    criptions
    -0.06
     ngồi
    -0.06
     red
    -0.06
    POSITIVE LOGITS
    ér
    0.07
    жения
    0.07
    高中
    0.06
     которого
    0.06
    )'↵
    0.06
    .TextChanged
    0.06
    ErrorMsg
    0.06
    :aload
    0.06
    】↵↵
    0.06
    :)↵
    0.06
    Act Density 0.057%

    No Known Activations