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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Changing
    -0.09
     Tmax
    -0.07
    舍
    -0.07
    冰
    -0.07
    TypeEnum
    -0.07
    ANC
    -0.07
     контак
    -0.07
    ώντας
    -0.07
    _rr
    -0.07
     feast
    -0.06
    POSITIVE LOGITS
     кас
    0.07
    ])-
    0.06
     дити
    0.06
     öff
    0.06
    '}↵↵
    0.06
    itoris
    0.06
    iselect
    0.06
     elemento
    0.06
    pcion
    0.05
     astore
    0.05
    Act Density 0.019%

    No Known Activations