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

    Neuronpedia

    INDEX
    Explanations

    geometric division

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    风险
    -0.09
     Risk
    -0.09
    -risk
    -0.09
    Risk
    -0.09
     risk
    -0.08
     risky
    -0.08
     dossiers
    -0.08
    <|start|>
    -0.08
     Cient
    -0.08
     synth
    -0.07
    POSITIVE LOGITS
    Entrance
    0.09
     macar
    0.08
     entrance
    0.08
     ورود
    0.08
     entrances
    0.08
     брон
    0.08
     peeling
    0.08
     отверст
    0.08
     odpow
    0.08
     corres
    0.07
    Act Density 0.051%

    No Known Activations