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

    Neuronpedia

    INDEX
    Explanations

    channel dimension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ués
    0.48
     agreeable
    0.48
    جمع
    0.47
     agrade
    0.46
     wobei
    0.46
    ANTIC
    0.46
     cười
    0.46
     Dí
    0.45
    止め
    0.45
     કર્મ
    0.45
    POSITIVE LOGITS
    linhas
    0.44
     informacion
    0.44
     _)
    0.43
    genheim
    0.42
    Cardinal
    0.42
    glTranslatef
    0.42
     다르
    0.41
    their
    0.41
    Menus
    0.41
    oug
    0.40
    Act Density 0.000%

    No Known Activations