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

    Neuronpedia

    INDEX
    Explanations

    say D or C

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    羓
    -0.09
    ォ
    -0.07
    delta
    -0.07
     alleged
    -0.06
    优雅
    -0.06
    =obj
    -0.06
    깉
    -0.06
    Ah
    -0.06
    볼
    -0.06
    	local
    -0.06
    POSITIVE LOGITS
    _Ptr
    0.08
    פע
    0.07
     slain
    0.07
     multitude
    0.07
     Reduction
    0.07
    ệm
    0.07
    一夜
    0.07
    pio
    0.07
    众所周
    0.07
    なくて
    0.07
    Act Density 0.014%

    No Known Activations