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

    Neuronpedia

    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     những
    -0.07
     Mech
    -0.07
    cription
    -0.07
    젠
    -0.07
    itimate
    -0.06
    <Member
    -0.06
     np
    -0.06
    htags
    -0.06
     ע
    -0.06
    훗
    -0.06
    POSITIVE LOGITS
    -install
    0.07
    比
    0.07
    刀
    0.07
    ...,
    0.07
    quick
    0.07
    .Dictionary
    0.06
    .face
    0.06
    aket
    0.06
    :error
    0.06
     ordinarily
    0.06
    Act Density 0.010%

    No Known Activations