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

    Neuronpedia

    INDEX
    Explanations

    ы

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    forcer
    -0.07
    Mix
    -0.06
     때
    -0.06
    泡
    -0.06
     potentials
    -0.06
    幸福
    -0.06
    scopes
    -0.06
    444
    -0.06
     sino
    -0.06
    .make
    -0.06
    POSITIVE LOGITS
    Contacts
    0.07
     Heg
    0.06
     타
    0.06
     oder
    0.06
     gradu
    0.06
     předch
    0.06
     suf
    0.06
     Athe
    0.06
     реб
    0.06
     evac
    0.06
    Act Density 0.007%

    No Known Activations