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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Salir
    -0.08
    nila
    -0.07
     historia
    -0.06
     pert
    -0.06
     contribution
    -0.06
     utiliser
    -0.06
    急
    -0.06
     Estado
    -0.06
     pian
    -0.06
    データ
    -0.06
    POSITIVE LOGITS
    iel
    0.07
    그러
    0.07
    อบ
    0.07
    ScreenState
    0.06
    허
    0.06
     kå
    0.06
     така
    0.06
     relentless
    0.06
    0.06
     그래서
    0.06
    Act Density 0.096%

    No Known Activations