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

    Neuronpedia

    INDEX
    Explanations

    ’s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncommon
    -0.06
    ारत
    -0.06
     campos
    -0.06
     müşter
    -0.06
     jeszcze
    -0.06
     kuk
    -0.06
     mantener
    -0.06
     yarat
    -0.06
    ergus
    -0.06
    .users
    -0.05
    POSITIVE LOGITS
     maximum
    0.07
     disciples
    0.07
    Dock
    0.07
     charg
    0.07
    .Caption
    0.06
     開
    0.06
     Coverage
    0.06
     було
    0.06
     apparel
    0.06
    ầm
    0.06
    Act Density 0.000%

    No Known Activations