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

    Neuronpedia

    INDEX
    Explanations

    dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raiſ
    -0.75
     nakalista
    -0.66
     ſtate
    -0.65
     Jefus
    -0.63
     Majefty
    -0.61
     ſta
    -0.61
     greateſt
    -0.60
     poffe
    -0.60
     neceff
    -0.59
     beſt
    -0.59
    POSITIVE LOGITS
    blurRadius
    0.50
     “
    0.44
     "
    0.44
     flop
    0.44
     виправивши
    0.42
     '
    0.41
    <#
    0.40
    ξης
    0.40
     ‘
    0.40
     dzied
    0.40
    Act Density 0.023%

    No Known Activations