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

    Neuronpedia

    INDEX
    Explanations

    in your or the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solche
    0.67
    Dieses
    0.65
    Such
    0.60
    Featuring
    0.59
    Seven
    0.56
     solchen
    0.56
    These
    0.55
    This
    0.53
    Nine
    0.53
     takich
    0.52
    POSITIVE LOGITS
     certificates
    0.63
     ~/
    0.63
     редакти
    0.62
     parentheses
    0.61
    foration
    0.60
     timestamps
    0.59
     Certificates
    0.58
     templates
    0.57
     separator
    0.57
     certificados
    0.56
    Act Density 0.027%

    No Known Activations