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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tues
    -1.09
     AIA
    -1.06
    agio
    -1.02
    usen
    -0.71
    liston
    -0.68
    lien
    -0.55
     متعلقه
    -0.53
     Sun
    -0.49
     seg
    -0.48
     degree
    -0.48
    POSITIVE LOGITS
    styleType
    0.87
    LEncoder
    0.83
    ArgsConstructor
    0.82
    AccessFile
    0.77
    出版年
    0.76
    othelioma
    0.73
    esgue
    0.73
    ंदीखरीदारी
    0.71
    StoryboardSegue
    0.69
    ształ
    0.69
    Act Density 0.603%

    No Known Activations