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

    Neuronpedia

    INDEX
    Explanations

    citizens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handlers
    -0.08
    _ignore
    -0.07
     gor
    -0.07
    υχ
    -0.07
     LI
    -0.06
     OH
    -0.06
    ever
    -0.06
    Ni
    -0.06
    ��
    -0.06
    elif
    -0.06
    POSITIVE LOGITS
    "]=>
    0.07
    )["
    0.06
     درمان
    0.06
     earnest
    0.06
    erah
    0.06
     زمان
    0.06
     onSuccess
    0.06
    ={['
    0.06
    ]->
    0.06
    =./
    0.06
    Act Density 0.015%

    No Known Activations