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

    Neuronpedia

    INDEX
    Explanations

    Instagram and social media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zu
    -1.57
     Zu
    -1.02
    Zu
    -1.02
    ZU
    -0.93
     zu
    -0.86
    sta
    -0.64
     ZU
    -0.60
     protoimpl
    -0.54
    su
    -0.51
    ste
    -0.47
    POSITIVE LOGITS
    AutoScaleMode
    0.59
    Personendaten
    0.56
    ädie
    0.54
    NewUrlParser
    0.53
    CloseOperation
    0.52
    omeness
    0.51
    requestCode
    0.51
    </tfoot>
    0.50
     Lut
    0.49
    Lut
    0.48
    Act Density 0.011%

    No Known Activations