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

    Neuronpedia

    INDEX
    Explanations

    support and reversal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    流域
    1.48
     সালের
    1.29
    রুখ
    1.23
    々な
    1.22
    SCAPE
    1.19
     precedence
    1.17
    DEFGHIJKLMNOP
    1.17
    ካት
    1.16
     रखता
    1.15
    สิ้น
    1.15
    POSITIVE LOGITS
    on
    1.66
    ли
    1.59
    و
    1.52
    in
    1.36
    ла
    1.36
    an
    1.26
    ல்
    1.26
    backed
    1.26
    re
    1.25
    en
    1.24
    Act Density 0.000%

    No Known Activations