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

    Neuronpedia

    INDEX
    Explanations

    `import` or `deployment`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     projected
    0.36
     Antony
    0.34
    ‍
    0.34
     antiviral
    0.34
    hek
    0.33
    وغ
    0.33
     delay
    0.32
     ega
    0.32
    }}.
    0.32
    ">{{
    0.32
    POSITIVE LOGITS
    हि
    0.31
    мен
    0.31
     entour
    0.31
    стве
    0.30
    cutta
    0.30
     exame
    0.30
    squiggle
    0.30
     படைய
    0.30
    ear
    0.29
     prostředí
    0.29
    Act Density 0.000%

    No Known Activations