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

    Neuronpedia

    INDEX
    Explanations

    access modifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Consumers
    -0.07
    سان
    -0.07
    	writer
    -0.07
    _terms
    -0.07
     boarded
    -0.07
     Haus
    -0.06
     لغ
    -0.06
     sailors
    -0.06
     Manit
    -0.06
     فلس
    -0.06
    POSITIVE LOGITS
    anglicky
    0.07
    DEPEND
    0.07
     confidently
    0.06
     dříve
    0.06
    .Sprintf
    0.06
     strapon
    0.06
    connecting
    0.06
     šť
    0.06
    Private
    0.06
    MAKE
    0.06
    Act Density 0.020%

    No Known Activations