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

    Neuronpedia

    INDEX
    Explanations

    fraction division mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mixer
    0.47
     Add
    0.47
    न्
    0.44
     Gen
    0.44
     Ad
    0.43
     Tall
    0.42
     tall
    0.41
     Shows
    0.41
     Conven
    0.40
     Organ
    0.39
    POSITIVE LOGITS
    eyeglasses
    0.45
    ㅀ
    0.43
    behav
    0.42
    amay
    0.42
    আগ
    0.42
    artifact
    0.41
    。【
    0.41
    WallArray
    0.40
    ammo
    0.40
    írez
    0.40
    Act Density 0.005%

    No Known Activations