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

    Neuronpedia

    INDEX
    Explanations

    Male

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sectors
    -0.07
     addressing
    -0.06
     volcano
    -0.06
     рас
    -0.06
    .world
    -0.06
    ITH
    -0.06
    _subtype
    -0.06
     Да
    -0.06
     ваг
    -0.06
    mpar
    -0.06
    POSITIVE LOGITS
    eview
    0.07
     thuisontvangst
    0.06
     Check
    0.06
    ，让
    0.06
    에
    0.06
    结
    0.06
     Sexe
    0.06
    ripe
    0.06
    rik
    0.06
     numer
    0.06
    Act Density 0.003%

    No Known Activations