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

    Neuronpedia

    INDEX
    Explanations

    multimodal capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.63
    in
    1.60
    w
    1.59
    y
    1.52
    o
    1.39
    at
    1.36
    s
    1.31
    n
    1.29
    ן
    1.23
    id
    1.22
    POSITIVE LOGITS
     όλ
    0.95
     antitumor
    0.83
    一块
    0.82
     ακ
    0.82
     formaldehyde
    0.81
     तरीका
    0.80
     cardiomyocyte
    0.79
    一套
    0.79
     copier
    0.78
     άλ
    0.77
    Act Density 0.008%

    No Known Activations