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

    Neuronpedia

    INDEX
    Explanations

    explaining causes and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.54
    面
    0.52
     *\
    0.50
    色
    0.48
    $
    0.45
     matriz
    0.44
     fall
    0.43
    Wind
    0.42
     a
    0.42
    Ха
    0.42
    POSITIVE LOGITS
    IsMethod
    0.55
    itih
    0.51
    hitva
    0.48
     відноси
    0.48
    prene
    0.47
     Tages
    0.47
     எத்தனை
    0.46
    gomery
    0.46
    ucumber
    0.45
    uw
    0.45
    Act Density 0.001%

    No Known Activations