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

    Neuronpedia

    INDEX
    Explanations

    le

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    主业
    -0.08
    REMOVE
    -0.07
    KP
    -0.07
    你还
    -0.07
    Diagnostic
    -0.07
    🤩
    -0.06
    $error
    -0.06
    퉈
    -0.06
    urdy
    -0.06
    'name
    -0.06
    POSITIVE LOGITS
     raison
    0.07
     conoc
    0.07
     Cox
    0.07
     התביעה
    0.07
    adena
    0.07
    液
    0.07
     Eaton
    0.07
     Albany
    0.06
    _soc
    0.06
    �
    0.06
    Act Density 0.008%

    No Known Activations