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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سوی
    -0.07
    /Typography
    -0.07
    RouterModule
    -0.07
     UIStoryboard
    -0.07
     Yardım
    -0.07
     LT
    -0.06
    %.↵↵
    -0.06
    .Slf
    -0.06
    _Real
    -0.06
     nto
    -0.06
    POSITIVE LOGITS
     пораж
    0.07
    iral
    0.07
    _exit
    0.06
    _hook
    0.06
    _regions
    0.06
    clidean
    0.06
     Russia
    0.06
    runs
    0.06
     месяца
    0.06
    Exit
    0.06
    Act Density 0.016%

    No Known Activations