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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    principalTable
    -0.59
    potranspiration
    -0.59
    Brainz
    -0.58
     varandra
    -0.58
     فريبيس
    -0.56
    QMetaType
    -0.55
     présidenti
    -0.55
     Pompey
    -0.53
    giveness
    -0.52
    Ozone
    -0.50
    POSITIVE LOGITS
     called
    0.75
     referred
    0.74
     CALLED
    0.69
    called
    0.66
     termed
    0.65
    Called
    0.63
    referred
    0.62
     Called
    0.62
     i
    0.60
     known
    0.59
    Act Density 0.001%

    No Known Activations