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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric character sequences in URLs

    oai_token-act-pair · gemini-2.0-flash

    Links/Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    l
    -0.79
    c
    -0.77
    r
    -0.72
     GenerationType
    -0.60
    f
    -0.57
    n
    -0.53
    b
    -0.52
    GenerationType
    -0.49
    p
    -0.47
     endforeach
    -0.47
    POSITIVE LOGITS
    stwa
    0.67
    Hochspringen
    0.60
    ArgsConstructor
    0.59
    Diweddarwch
    0.57
     obé
    0.56
     الرياضيه
    0.56
    loride
    0.55
    cshtml
    0.55
    UnusedPrivate
    0.54
     Geraadpleegd
    0.53
    Act Density 0.933%

    No Known Activations