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

    Neuronpedia

    INDEX
    Explanations

    code assignments and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ของการ
    0.36
    ण्यास
    0.35
     vib
    0.33
     detonations
    0.33
     Messrs
    0.32
     Dap
    0.32
     육
    0.32
     plaintiff
    0.31
    ຂໍ້ມູນ
    0.31
    缺乏
    0.30
    POSITIVE LOGITS
    佢
    0.60
     ĝi
    0.55
    它
    0.55
     它
    0.53
     it
    0.52
    它们
    0.50
    其
    0.49
     אותו
    0.47
     niego
    0.47
     them
    0.46
    Act Density 0.062%

    No Known Activations