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

    Neuronpedia

    INDEX
    Explanations

    CM and CM-like acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cton
    0.40
    stige
    0.39
     UR
    0.38
     Saba
    0.38
     отца
    0.38
    ursor
    0.38
    にする
    0.37
    cliff
    0.37
    次的
    0.37
     доби
    0.37
    POSITIVE LOGITS
     CM
    0.79
     cm
    0.67
    CM
    0.66
     सीएम
    0.63
    cm
    0.61
    YK
    0.61
     Cm
    0.61
     CMS
    0.59
     cms
    0.59
    सीएम
    0.57
    Act Density 0.005%

    No Known Activations