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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    道歉
    -0.08
     onload
    -0.08
    StateToProps
    -0.07
     "../../../../
    -0.07
    PRESENT
    -0.07
    東
    -0.07
     billeder
    -0.07
     прек
    -0.07
    NOT
    -0.06
    ᒌ
    -0.06
    POSITIVE LOGITS
    蓄电池
    0.06
     enjoys
    0.06
    _component
    0.06
    蕴含
    0.06
    .ent
    0.06
    metrics
    0.06
     lending
    0.06
    Bucket
    0.06
    _utils
    0.06
    abolic
    0.06
    Act Density 0.000%

    No Known Activations