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

    Neuronpedia

    INDEX
    Explanations

    Chemical notations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entů
    -0.08
    poň
    -0.07
    нциклопед
    -0.06
    inger
    -0.06
    eping
    -0.06
    ír
    -0.06
     업데이트
    -0.06
    �
    -0.06
     tělo
    -0.06
     먼
    -0.06
    POSITIVE LOGITS
     Quentin
    0.07
     Critics
    0.06
    igin
    0.06
    Mov
    0.06
    fab
    0.06
     c
    0.06
     abusing
    0.06
     grateful
    0.06
     Krishna
    0.06
     Jeremy
    0.06
    Act Density 0.008%

    No Known Activations