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

    Neuronpedia

    INDEX
    Explanations

    multi-script sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     البته
    0.25
    ycl
    0.25
    igation
    0.24
    েন
    0.24
    ču
    0.24
    entimes
    0.24
    0.24
     یک
    0.23
     причем
    0.23
     lo
    0.23
    POSITIVE LOGITS
     aplatis
    0.31
     roka
    0.31
     flancs
    0.27
     halal
    0.27
     skates
    0.27
     bleue
    0.27
     correctes
    0.26
     яких
    0.26
     carénés
    0.25
     rollerskates
    0.25
    Act Density 0.092%

    No Known Activations