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

    Neuronpedia

    INDEX
    Explanations

    specific font names and styles

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

    font names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.78
    
    -0.71
    Hentet
    -0.60
    +#+#
    -0.59
    IBAction
    -0.58
    󠁬
    -0.57
    Билгалдахарш
    -0.57
    تقاوى
    -0.57
    httphttps
    -0.55
    UnusedPrivate
    -0.54
    POSITIVE LOGITS
    Roboto
    0.75
    Segoe
    0.63
    Poppins
    0.60
    Helvetica
    0.44
    Arial
    0.44
    AnchorStyles
    0.42
    Lato
    0.35
     stiffness
    0.35
     veau
    0.35
    tserrat
    0.35
    Act Density 0.001%

    No Known Activations