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

    Neuronpedia

    INDEX
    Explanations

    it through something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    寘
    0.67
     terletak
    0.67
    ∂</
    0.66
    periodic
    0.65
     sajana
    0.64
    ומים
    0.64
    Mannschaft
    0.63
     cứng
    0.63
     obecnie
    0.63
    にする
    0.63
    POSITIVE LOGITS
     through
    3.53
    through
    2.95
     Through
    2.94
     thru
    2.80
    Through
    2.75
     attraverso
    2.75
     THROUGH
    2.65
     melalui
    2.44
     através
    2.36
     gjennom
    2.33
    Act Density 0.602%

    No Known Activations