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

    Neuronpedia

    INDEX
    Explanations

    I cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asegurar
    0.42
     Kast
    0.39
    𒂠
    0.39
     ACA
    0.39
     نحل
    0.39
     செய்வது
    0.38
    اعة
    0.38
     Packages
    0.38
     shells
    0.38
    adeep
    0.38
    POSITIVE LOGITS
    moment
    0.42
    Tight
    0.40
     benefitting
    0.40
    veranst
    0.40
    noscript
    0.39
    rope
    0.39
    Aud
    0.38
    genre
    0.37
    Fall
    0.36
    Obst
    0.36
    Act Density 0.000%

    No Known Activations