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

    Neuronpedia

    INDEX
    Explanations

    analyze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TypeDef
    -0.08
    _handlers
    -0.06
     Brit
    -0.06
     chuẩn
    -0.06
    _CAM
    -0.06
     tint
    -0.06
     gathered
    -0.06
     влия
    -0.06
    .getPassword
    -0.06
    حية
    -0.06
    POSITIVE LOGITS
     Uns
    0.07
     esi
    0.07
    ojí
    0.07
    artist
    0.07
    —one
    0.07
     Rogers
    0.06
     glaciers
    0.06
    머니
    0.06
     stalking
    0.06
     nemůže
    0.06
    Act Density 0.000%

    No Known Activations