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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iž
    -0.07
    (al
    -0.06
    licts
    -0.06
     Pat
    -0.06
    .exp
    -0.06
    (cnt
    -0.06
    Ack
    -0.06
     anonymity
    -0.06
    ятие
    -0.06
     condemnation
    -0.06
    POSITIVE LOGITS
    ython
    0.07
     vowed
    0.07
    ウォ
    0.06
    \uC
    0.06
    ":"","
    0.06
    RIC
    0.06
     перев
    0.06
    とき
    0.06
    numeric
    0.06
     ARTICLE
    0.06
    Act Density 0.005%

    No Known Activations