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

    Neuronpedia

    INDEX
    Explanations

    setup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    퓨터
    -0.06
    Been
    -0.06
     виг
    -0.06
    Turn
    -0.06
    免
    -0.06
     cứ
    -0.06
     stumbled
    -0.06
    NonNull
    -0.06
    :'',↵
    -0.06
     тих
    -0.06
    POSITIVE LOGITS
     стало
    0.06
    'article
    0.06
    	UP
    0.06
     Sky
    0.06
    _lb
    0.06
    _process
    0.06
     BETWEEN
    0.06
     damages
    0.06
     toastr
    0.06
     sayılı
    0.06
    Act Density 0.039%

    No Known Activations