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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Май
    -0.06
     texting
    -0.06
     intimately
    -0.06
    _ONE
    -0.06
     bbw
    -0.06
    Hour
    -0.06
     ku
    -0.06
    uarios
    -0.06
     floppy
    -0.06
     THR
    -0.06
    POSITIVE LOGITS
    [S
    0.07
     Defendant
    0.07
    cdecl
    0.07
    628
    0.07
    737
    0.07
    getTable
    0.07
     permutations
    0.07
     bitch
    0.07
    返回
    0.06
    пол
    0.06
    Act Density 0.007%

    No Known Activations