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

    Neuronpedia

    INDEX
    Explanations

    looking for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endment
    1.22
    oram
    1.13
     LMFBR
    1.13
     encuentros
    1.13
    쐞
    1.10
    ています
    1.09
    ンの
    1.07
    qx
    1.07
    说说
    1.07
    erequisite
    1.07
    POSITIVE LOGITS
    ↵↵
    1.45
    druck
    1.22
    дно
    1.16
     lull
    1.13
    dan
    1.09
    ни
    1.07
    ش
    1.07
    din
    1.06
    я
    1.05
    лег
    1.05
    Act Density 0.004%

    No Known Activations