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

    Neuronpedia

    INDEX
    Explanations

    Japanese history and names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liest
    -0.08
     ذکر
    -0.07
    achts
    -0.07
    aments
    -0.07
    つ
    -0.06
    PLEMENT
    -0.06
    روط
    -0.06
     quand
    -0.06
    halt
    -0.06
    .Write
    -0.06
    POSITIVE LOGITS
     unsus
    0.07
    ():
↵
    0.06
    .SM
    0.06
    име
    0.06
     AuthenticationService
    0.06
     SUM
    0.06
     unseen
    0.06
     nationally
    0.06
     }↵↵↵↵↵↵
    0.06
     tiny
    0.06
    Act Density 0.014%

    No Known Activations