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

    Neuronpedia

    INDEX
    Explanations

    firearm actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	has
    -0.07
    していく
    -0.07
    を考え
    -0.07
    history
    -0.07
    	ll
    -0.07
    的目的
    -0.06
     ll
    -0.06
    _Location
    -0.06
    历代
    -0.06
    .↵↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    游击
    0.07
    ilter
    0.07
    难忘
    0.07
    خفض
    0.07
     trigger
    0.07
     keyed
    0.07
    ཏ
    0.07
    痴迷
    0.07
    �
    0.07
    _trigger
    0.06
    Act Density 0.014%

    No Known Activations