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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ése
    -0.07
    专家组
    -0.07
    ác
    -0.07
     הטיפול
    -0.07
    rese
    -0.07
    DataAdapter
    -0.07
     darauf
    -0.06
    各方
    -0.06
     piping
    -0.06
     tahun
    -0.06
    POSITIVE LOGITS
     Emotional
    0.07
    遆
    0.07
     HOLD
    0.07
    emsp
    0.07
     Montreal
    0.07
     Beck
    0.06
     Loans
    0.06
     Mockito
    0.06
    .elementAt
    0.06
    ኮ
    0.06
    Act Density 0.003%

    No Known Activations