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

    Neuronpedia

    INDEX
    Explanations

    Code/configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     may
    -0.85
     lenker
    -0.85
     الرياضيه
    -0.72
     might
    -0.71
    rungsseite
    -0.67
     automatiques
    -0.67
    <?
    -0.67
     متعلقه
    -0.65
    TagHelper
    -0.63
     خارجية
    -0.63
    POSITIVE LOGITS
    dn
    0.47
    displayquote
    0.45
    stood
    0.43
    igram
    0.42
     lob
    0.42
     respaldo
    0.41
     проводи
    0.41
    رها
    0.41
     recast
    0.40
     Lor
    0.40
    Act Density 1.527%

    No Known Activations