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

    Neuronpedia

    INDEX
    Explanations

    Ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occupied
    -0.52
     fault
    -0.51
    Fault
    -0.51
     Artificial
    -0.49
    Artificial
    -0.49
    思います
    -0.49
    celli
    -0.47
     Fault
    -0.47
    SO
    -0.46
     Note
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.86
     дописавши
    0.84
    出版年
    0.83
    UVWXYZ
    0.81
    DeleteBehavior
    0.79
    homonymie
    0.72
     unknownFields
    0.71
     ModelExpression
    0.70
     '\\;'
    0.69
    انيف
    0.69
    Act Density 0.184%

    No Known Activations