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

    Neuronpedia

    INDEX
    Explanations

    conferences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ournals
    -0.08
    	req
    -0.06
     cured
    -0.06
    ped
    -0.06
     disables
    -0.06
     eh
    -0.06
    uits
    -0.06
     wiki
    -0.06
     أو
    -0.06
     assist
    -0.06
    POSITIVE LOGITS
    _________________↵↵
    0.07
    伦
    0.06
    pagen
    0.06
     daemon
    0.06
    .role
    0.06
    在线观看
    0.06
    <Tag
    0.06
    ộ
    0.06
    ửa
    0.06
    '},
↵
    0.06
    Act Density 0.037%

    No Known Activations