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

    Neuronpedia

    INDEX
    Explanations

    improper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thần
    -0.07
     záznam
    -0.07
     نص
    -0.07
    111
    -0.06
     luck
    -0.06
    --------------
    -0.06
    ｗｗ
    -0.06
    FRINGEMENT
    -0.06
    ].[
    -0.06
    哈
    -0.06
    POSITIVE LOGITS
     improper
    0.13
     improperly
    0.08
     immedi
    0.07
     영향을
    0.07
     dps
    0.07
    (secret
    0.06
    λο
    0.06
    groups
    0.06
    Producer
    0.06
    gary
    0.06
    Act Density 0.002%

    No Known Activations