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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     також
    -0.06
     "\"
    -0.06
    !!,
    -0.06
    vie
    -0.06
    ////////////////////////////////////////////////
    -0.06
     přisp
    -0.06
    oodles
    -0.06
    Spaces
    -0.06
     fisse
    -0.06
    brain
    -0.06
    POSITIVE LOGITS
     thôn
    0.07
     fields
    0.06
    ector
    0.06
     countered
    0.06
    .res
    0.06
    τερα
    0.06
     власти
    0.06
    straint
    0.06
     tariffs
    0.06
     filed
    0.06
    Act Density 0.003%

    No Known Activations