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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    合影
    -0.06
    .Copy
    -0.06
    dojo
    -0.06
    imore
    -0.06
    (case
    -0.06
     boob
    -0.06
    死亡
    -0.06
    ließ
    -0.06
    _DEPTH
    -0.06
     họp
    -0.06
    POSITIVE LOGITS
     כ
    0.07
    ,$
    0.07
     advised
    0.07
     flash
    0.07
    	card
    0.07
     },↵
    0.07
     Irish
    0.07
    (sprite
    0.07
    高校
    0.06
    .yml
    0.06
    Act Density 0.004%

    No Known Activations