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

    Neuronpedia

    INDEX
    Explanations

    use of force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uttgart
    -0.06
    �
    -0.06
    炉
    -0.06
     Prod
    -0.06
     dry
    -0.06
    .statusStrip
    -0.06
     Starting
    -0.06
     worldly
    -0.06
    clock
    -0.06
    tone
    -0.06
    POSITIVE LOGITS
    zeń
    0.07
     Israeli
    0.06
     Ell
    0.06
     meisten
    0.06
    ancial
    0.06
     meinem
    0.06
     cleaned
    0.06
    aların
    0.06
    auc
    0.06
    osloven
    0.06
    Act Density 0.095%

    No Known Activations