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

    Neuronpedia

    INDEX
    Explanations

    parallel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equals
    -0.07
     Exactly
    -0.07
    venience
    -0.07
    稳
    -0.07
    _bc
    -0.07
     Represents
    -0.07
     ·
    -0.07
     بك
    -0.06
    )/
    -0.06
    :L
    -0.06
    POSITIVE LOGITS
     blaze
    0.07
    掌门
    0.07
     erotiske
    0.07
    ยก
    0.07
    焚烧
    0.07
    (Task
    0.07
    夏日
    0.06
     heter
    0.06
    Assignable
    0.06
    FormatException
    0.06
    Act Density 0.013%

    No Known Activations