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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     referred
    -0.07
    �
    -0.07
     heavily
    -0.07
    ชาว
    -0.07
     host
    -0.07
    čil
    -0.06
     Ø
    -0.06
     Основ
    -0.06
     predictions
    -0.06
     cane
    -0.06
    POSITIVE LOGITS
     APK
    0.06
    .AddInParameter
    0.06
    _shortcode
    0.06
     χ
    0.06
    .ModelForm
    0.06
     vielleicht
    0.06
    atrix
    0.06
     �
    0.06
    níku
    0.06
    Dirs
    0.06
    Act Density 0.023%

    No Known Activations