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

    Neuronpedia

    INDEX
    Explanations

    determines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.94
     <=",
    -0.94
    AntiForgeryToken
    -0.90
    évaluateur
    -0.86
    SequentialGroup
    -0.86
    IndentedString
    -0.86
    StructEnd
    -0.85
    protoimpl
    -0.84
    енча
    -0.84
     betweenstory
    -0.80
    POSITIVE LOGITS
     we
    0.51
     Schließlich
    0.41
     the
    0.41
     We
    0.40
     того
    0.40
    htë
    0.40
     why
    0.40
    ográfico
    0.40
     that
    0.38
     He
    0.38
    Act Density 0.001%

    No Known Activations