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

    Neuronpedia

    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     missions
    -0.07
    itas
    -0.06
    stem
    -0.06
     pocit
    -0.06
     badass
    -0.06
     picks
    -0.06
    IFF
    -0.06
    .std
    -0.06
     spinning
    -0.06
    .mid
    -0.06
    POSITIVE LOGITS
     Barcelona
    0.06
     موفق
    0.06
    になり
    0.06
    ивают
    0.06
     POL
    0.06
     형
    0.06
     Вар
    0.06
    онах
    0.06
     tabi
    0.06
     Wel
    0.06
    Act Density 0.002%

    No Known Activations