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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    …↵↵↵
    -0.07
    797
    -0.06
     })↵
    -0.06
    /settingsdialog
    -0.06
    okane
    -0.06
    azing
    -0.06
     grinned
    -0.06
    厚
    -0.06
     electoral
    -0.06
    Topic
    -0.06
    POSITIVE LOGITS
    _person
    0.07
     FILE
    0.07
    (),"
    0.06
    Sparse
    0.06
     CPL
    0.06
    追加
    0.06
    土
    0.06
    /export
    0.06
     Detector
    0.06
    Combined
    0.06
    Act Density 0.017%

    No Known Activations