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

    Neuronpedia

    INDEX
    Explanations

    nel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     מאו
    -0.07
     ACPI
    -0.06
    acman
    -0.06
    偕
    -0.06
     ordered
    -0.06
    に基
    -0.06
    蛔
    -0.06
     đứng
    -0.06
    Luck
    -0.06
    ڛ
    -0.06
    POSITIVE LOGITS
     //////////////////
    0.08
    hazi
    0.07
    流程
    0.07
    ieving
    0.07
     Ended
    0.07
    主权
    0.07
    感受
    0.07
    _TRA
    0.07
     }}"></
    0.07
     finalist
    0.07
    Act Density 0.001%

    No Known Activations