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

    Neuronpedia

    INDEX
    Explanations

    Undiscussed/overlooked topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     уд
    -0.07
     abund
    -0.07
    olley
    -0.07
     genome
    -0.06
    ль
    -0.06
    .DOM
    -0.06
    ЛЬ
    -0.06
    bestos
    -0.06
    relay
    -0.06
    atement
    -0.06
    POSITIVE LOGITS
     Merch
    0.07
     نوفمبر
    0.06
    PreferredGap
    0.06
    .Diagnostics
    0.06
     tours
    0.06
     legalize
    0.06
     aquí
    0.06
     자세
    0.06
    -court
    0.06
     :+:
    0.06
    Act Density 0.064%

    No Known Activations