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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing qualities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keine
    -0.07
     Các
    -0.07
    .ERROR
    -0.07
    Diese
    -0.07
    Pow
    -0.06
    Saving
    -0.06
    /~
    -0.06
     meget
    -0.06
    Earn
    -0.06
     anche
    -0.06
    POSITIVE LOGITS
    kov
    0.08
    outlined
    0.07
     phot
    0.07
     fatto
    0.06
     approve
    0.06
     mama
    0.06
    ZE
    0.06
    logy
    0.06
    _UNIFORM
    0.06
    proto
    0.06
    Act Density 0.045%

    No Known Activations