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

    Neuronpedia

    INDEX
    Explanations

    stration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']+
    -0.07
     Liberals
    -0.06
     примен
    -0.06
     problémy
    -0.06
     extrad
    -0.06
    ид
    -0.06
    Probably
    -0.06
    Neither
    -0.06
     sweets
    -0.06
    _visited
    -0.06
    POSITIVE LOGITS
    νονται
    0.07
    -viol
    0.07
     geometric
    0.06
     AngularFire
    0.06
     Fla
    0.06
    Unmarshaller
    0.06
    -Level
    0.06
     damaging
    0.06
    []{↵
    0.06
    147
    0.06
    Act Density 0.000%

    No Known Activations