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

    Neuronpedia

    INDEX
    Explanations

    cuts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าซ
    -0.06
    queen
    -0.06
    Bern
    -0.06
    visibility
    -0.06
    umpy
    -0.06
     فرز
    -0.06
     FOLLOW
    -0.06
     робот
    -0.06
     superv
    -0.06
     Task
    -0.06
    POSITIVE LOGITS
    CGFloat
    0.07
    CKET
    0.07
     Ε
    0.07
    omore
    0.06
    .Visual
    0.06
    나요
    0.06
    .ImageField
    0.06
    _CRITICAL
    0.06
     Paragraph
    0.06
     reductions
    0.06
    Act Density 0.015%

    No Known Activations