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

    Neuronpedia

    INDEX
    Explanations

    technical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    require
    -0.95
     require
    -0.88
     Require
    -0.85
    Require
    -0.84
     prepared
    -0.83
     chrétienne
    -0.77
     préparé
    -0.77
     Prepared
    -0.74
     preparada
    -0.73
    prepared
    -0.72
    POSITIVE LOGITS
     the
    0.70
     its
    0.66
     their
    0.64
     a
    0.64
    曖昧さ回避
    0.62
     ra
    0.61
    tvguidetime
    0.60
    homonymie
    0.59
     early
    0.58
     this
    0.56
    Act Density 0.112%

    No Known Activations