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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    спект
    -0.07
    (angle
    -0.07
    积累了
    -0.07
     hills
    -0.07
     invoking
    -0.07
     indexOf
    -0.06
    _refresh
    -0.06
     acompanh
    -0.06
    .games
    -0.06
    .erase
    -0.06
    POSITIVE LOGITS
    훵
    0.07
    代孕
    0.07
    irie
    0.07
     hospital
    0.07
     października
    0.07
     british
    0.07
    重度
    0.06
    .not
    0.06
    :');↵
    0.06
    前身
    0.06
    Act Density 0.006%

    No Known Activations