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

    Neuronpedia

    INDEX
    Explanations

    creative works titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devoted
    -0.07
    (st
    -0.06
     кроме
    -0.06
    _hover
    -0.06
    .train
    -0.06
    wagon
    -0.06
     Award
    -0.06
     beet
    -0.06
     Oper
    -0.06
     HashSet
    -0.06
    POSITIVE LOGITS
     پزشکی
    0.07
    ιλο
    0.07
    icaid
    0.06
     podmínek
    0.06
    ibil
    0.06
    _ENDIAN
    0.06
    ilmektedir
    0.06
     Sydney
    0.06
     formulas
    0.06
     GE
    0.06
    Act Density 0.000%

    No Known Activations