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

    Neuronpedia

    INDEX
    Explanations

    list or array

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schaden
    0.81
     Bathroom
    0.76
     bathroom
    0.73
     NOC
    0.72
     liquor
    0.72
    swan
    0.71
     रेट
    0.69
    酒
    0.69
     Deaths
    0.68
     overpower
    0.68
    POSITIVE LOGITS
    数组
    2.47
     arrays
    2.36
     array
    2.30
    Array
    2.20
     Array
    2.19
     배열
    2.17
    array
    2.14
     Arrays
    2.13
    配列
    2.08
    arrays
    2.07
    Act Density 1.507%

    No Known Activations