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

    Neuronpedia

    INDEX
    Explanations

    non-verbal representations or placeholders in a document

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

    user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.80
    хьтан
    -0.73
    UserScript
    -0.72
    forName
    -0.67
    SequentialGroup
    -0.67
    XMLSchema
    -0.66
    styleType
    -0.66
     nahilalakip
    -0.65
    niſſe
    -0.64
     témoig
    -0.63
    POSITIVE LOGITS
    
    1.03
     
    0.93
    .
    0.73
    
    0.63
     Schulter
    0.41
     Zelt
    0.39
    assertj
    0.38
    Throwable
    0.38
     útiles
    0.37
    Źródło
    0.35
    Act Density 0.001%

    No Known Activations