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

    Neuronpedia

    INDEX
    Explanations

    explaining complex or diverse subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     получил
    0.53
     Minecraft
    0.51
     получила
    0.51
    бята
    0.48
     Chrome
    0.47
     Nantes
    0.47
     cómoda
    0.46
     держать
    0.46
     माप
    0.46
    耐
    0.46
    POSITIVE LOGITS
     heterogeneity
    0.58
     penetrate
    0.56
     multifaceted
    0.52
     constitutive
    0.51
    simeq
    0.50
     heterogeneous
    0.50
     cosmological
    0.49
     penetrated
    0.48
     penetrates
    0.48
     metaphors
    0.47
    Act Density 0.049%

    No Known Activations