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

    Neuronpedia

    INDEX
    Explanations

    cylindrical or elongated objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ש
    0.76
    то
    0.69
    ام
    0.67
    有一天
    0.66
     July
    0.64
    ף
    0.64
    м
    0.63
    ни
    0.62
     crebre
    0.61
    л
    0.61
    POSITIVE LOGITS
     rod
    0.68
     rods
    0.67
    逶
    0.64
     дерева
    0.62
     wires
    0.60
    两侧
    0.60
    এ
    0.60
     الصل
    0.59
    杆
    0.59
    ેશ
    0.59
    Act Density 0.119%

    No Known Activations