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

    Neuronpedia

    INDEX
    Explanations

    code block endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nich
    -0.11
    ottie
    -0.09
    ':''
    -0.09
    sla
    -0.08
    ลา
    -0.08
    ı
    -0.08
     Secondly
    -0.08
     idle
    -0.08
    alez
    -0.08
     tide
    -0.08
    POSITIVE LOGITS
    seealso
    0.10
    _contin
    0.09
     addCriterion
    0.08
    /ï¼ı
    0.08
    0.08
    ustos
    0.08
     {{\n
    0.08
    shima
    0.08
    å¤ĩ注
    0.08
    Âłmiles
    0.08
    Act Density 0.029%

    No Known Activations