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

    Neuronpedia

    INDEX
    Explanations

    references to scores and statistical outcomes in competitive scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    score prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.52
     JEE
    -0.43
    ThroughAttribute
    -0.42
    ligheten
    -0.42
    laub
    -0.42
    StructEnd
    -0.41
    ыгана
    -0.40
    CWE
    -0.40
     Шта
    -0.40
    原始内容存档于
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.59
     المعيارى
    0.55
    rungsseite
    0.51
    twimg
    0.50
    bootstrapcdn
    0.49
     disambiguazione
    0.48
     propOrder
    0.48
    PerformLayout
    0.48
    Jeografia
    0.46
    лтамалар
    0.46
    Act Density 0.101%

    No Known Activations