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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reputable
    -0.07
     conceived
    -0.06
     FEMA
    -0.06
    .Selection
    -0.06
    Scott
    -0.06
     합니다
    -0.06
    (Art
    -0.06
    AllowAnonymous
    -0.06
    .Output
    -0.06
    頻
    -0.06
    POSITIVE LOGITS
     waves
    0.06
    _coeff
    0.06
     нас
    0.06
     ghosts
    0.06
    čas
    0.06
    ],$
    0.06
     Thames
    0.06
     이용
    0.06
     Boh
    0.06
    rose
    0.06
    Act Density 0.009%

    No Known Activations