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

    Neuronpedia

    INDEX
    Explanations

    the word "Dark" and words with strong negative connotations.

    oai_token-act-pair · gemini-2.0-flash

    dark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dark
    -3.17
     Dark
    -2.92
    Dark
    -2.86
    dark
    -2.86
     DARK
    -2.67
    DARK
    -2.45
     darker
    -2.31
     darkest
    -1.91
     darkened
    -1.86
     darken
    -1.84
    POSITIVE LOGITS
    Javadoc
    0.58
    /**
    0.57
    GenerationType
    0.46
    XMLSchema
    0.44
    IOException
    0.42
    hynch
    0.42
    falt
    0.41
    asymp
    0.41
     Eind
    0.41
    etra
    0.40
    Act Density 3.046%

    No Known Activations