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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and positive interactions

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

    Unusual punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    user prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.50
    PMailer
    -0.44
    UrlResolution
    -0.41
     Eigentum
    -0.41
     insuffisamment
    -0.39
     Reſ
    -0.39
    sprogramm
    -0.39
    IsContent
    -0.38
    envolvimento
    -0.37
     ministres
    -0.36
    POSITIVE LOGITS
     ब्रेकडाउन
    0.57
     surla
    0.57
     <<<<<<<<<<<<<<
    0.51
     Rational
    0.44
    Neat
    0.43
    ]")]
    0.43
    談社
    0.42
    icksburg
    0.42
     AssemblyTitle
    0.42
     Anch
    0.41
    Act Density 0.072%

    No Known Activations