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

    Neuronpedia

    INDEX
    Explanations

    Email lists and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thigh
    -0.07
     looked
    -0.07
     passes
    -0.07
     interacting
    -0.07
    ormal
    -0.07
     Gry
    -0.06
     unchanged
    -0.06
     ils
    -0.06
    ASHINGTON
    -0.06
    té
    -0.06
    POSITIVE LOGITS
     dolay
    0.07
    .pages
    0.07
     доказ
    0.06
    >F
    0.06
     tarihli
    0.06
     //</
    0.06
    ен
    0.06
    주의
    0.06
    同
    0.06
    _system
    0.06
    Act Density 0.000%

    No Known Activations