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

    Neuronpedia

    INDEX
    Explanations

    risks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    release
    -0.07
     grow
    -0.07
     Sniper
    -0.07
     canopy
    -0.06
     variance
    -0.06
    clean
    -0.06
    -field
    -0.06
     freely
    -0.06
     Nobody
    -0.06
     art
    -0.06
    POSITIVE LOGITS
     risks
    0.27
     Ris
    0.08
     dangers
    0.07
    感觉
    0.07
    Minnesota
    0.07
    .Password
    0.07
     Citizenship
    0.06
     транспор
    0.06
    erre
    0.06
    /cards
    0.06
    Act Density 0.009%

    No Known Activations