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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    誉
    -0.07
    AccessToken
    -0.07
    Falsy
    -0.07
    STS
    -0.06
     Swe
    -0.06
     Circus
    -0.06
    iêng
    -0.06
    ализи
    -0.06
     हज
    -0.06
     Symptoms
    -0.06
    POSITIVE LOGITS
     podcast
    0.06
    unting
    0.06
    opup
    0.06
     dealing
    0.06
    (win
    0.06
    +t
    0.06
     ±
    0.06
     wrestling
    0.06
     forex
    0.06
     waiting
    0.06
    Act Density 0.000%

    No Known Activations