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

    Neuronpedia

    INDEX
    Explanations

    end up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     человеку
    0.36
     եւ
    0.34
    特效
    0.33
    хід
    0.33
    சியம்
    0.32
    及び
    0.32
    Ле
    0.32
     فورم
    0.32
     Ле
    0.32
    𝑉
    0.31
    POSITIVE LOGITS
     up
    0.54
     with
    0.45
     landed
    0.45
     aterriz
    0.41
     having
    0.41
     breathless
    0.41
     needing
    0.40
     parked
    0.39
     stranded
    0.38
     embroiled
    0.38
    Act Density 0.008%

    No Known Activations