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

    Neuronpedia

    INDEX
    Explanations

    binder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ++
    -0.07
     安
    -0.07
     Established
    -0.06
     altitude
    -0.06
    allowed
    -0.06
    att
    -0.06
    Shadow
    -0.06
    SN
    -0.06
    365
    -0.06
     spices
    -0.06
    POSITIVE LOGITS
     συ
    0.06
    .firstname
    0.06
     다
    0.06
     Injury
    0.06
    .Throws
    0.06
     입
    0.06
    _intr
    0.06
    (actor
    0.06
    *)↵↵
    0.06
     нер
    0.06
    Act Density 0.003%

    No Known Activations