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

    Neuronpedia

    INDEX
    Explanations

    unique comparison points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗪
    0.53
    𝘄
    0.48
    全体の
    0.47
    𝐯
    0.47
    有意
    0.45
    𝘀
    0.45
    chio
    0.44
    ための
    0.44
    themed
    0.44
    𝗬
    0.44
    POSITIVE LOGITS
    .
    0.50
     Physical
    0.48
     Database
    0.47
     Don
    0.46
    ]
    0.46
     phys
    0.45
     Decre
    0.45
     D
    0.45
     Physi
    0.45
     Acquire
    0.44
    Act Density 0.004%

    No Known Activations