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

    Neuronpedia

    INDEX
    Explanations

    computed/derived values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sow
    -0.08
     Kauf
    -0.08
     встрет
    -0.08
     overhaul
    -0.07
     uphe
    -0.07
    Verb
    -0.07
     Jul
    -0.07
     inoc
    -0.07
     exchange
    -0.07
    .se
    -0.07
    POSITIVE LOGITS
    computed
    0.14
     계산
    0.14
     calculates
    0.13
     Calculates
    0.13
    derived
    0.13
     calcula
    0.13
    calculate
    0.13
     вычис
    0.13
    Calculated
    0.13
    calcul
    0.12
    Act Density 0.019%

    No Known Activations