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

    Neuronpedia

    INDEX
    Explanations

    cross country races

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EL
    -1.34
    EM
    -1.31
    *
    -1.17
    AB
    -1.16
    mg
    -1.15
    =
    -1.14
     सि
    -1.13
    !
    -1.13
    Is
    -1.10
    -
    -1.10
    POSITIVE LOGITS
     десер
    1.38
    碛
    1.34
    咽
    1.30
    🅣
    1.30
     atmosf
    1.26
    cessions
    1.25
    FOLIO
    1.25
    ROOMS
    1.24
    ród
    1.24
    COCK
    1.23
    Act Density 0.021%

    No Known Activations