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

    Neuronpedia

    INDEX
    Explanations

    room

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enson
    -0.09
     irré
    -0.09
    итера
    -0.08
     Anch
    -0.08
    ირდება
    -0.08
     προϊόν
    -0.08
     anchors
    -0.08
    насці
    -0.08
    Anch
    -0.08
     fordert
    -0.08
    POSITIVE LOGITS
     opportunity
    0.11
    Opportunity
    0.10
     Opportunity
    0.10
     permiss
    0.10
     vacant
    0.09
    (low
    0.09
     advantage
    0.09
    无人
    0.09
    _unused
    0.09
    没人
    0.09
    Act Density 0.137%

    No Known Activations