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

    Neuronpedia

    INDEX
    Explanations

    NOT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uğra
    -0.07
     Kabul
    -0.06
     Luo
    -0.06
     فروش
    -0.06
    mium
    -0.06
     basal
    -0.06
    enderror
    -0.06
     congen
    -0.06
    ,rp
    -0.06
    scri
    -0.06
    POSITIVE LOGITS
    ротив
    0.07
     Authentication
    0.07
     fighters
    0.07
     Jury
    0.06
     mů
    0.06
     thao
    0.06
    -step
    0.06
    implicitly
    0.06
    ैत
    0.06
    ılığıyla
    0.06
    Act Density 0.001%

    No Known Activations