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

    Neuronpedia

    INDEX
    Explanations

    British history in 1600s

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Estado
    -0.07
     в
    -0.07
    Compound
    -0.07
     compiler
    -0.06
    Door
    -0.06
    rupt
    -0.06
     raising
    -0.06
    Sanders
    -0.06
     ortak
    -0.06
    _String
    -0.06
    POSITIVE LOGITS
    态
    0.06
    ává
    0.06
    _episode
    0.06
    응
    0.06
    534
    0.06
     Fif
    0.06
    tera
    0.06
    _Game
    0.06
    _APPRO
    0.06
    _EXIT
    0.06
    Act Density 0.008%

    No Known Activations