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

    Neuronpedia

    INDEX
    Explanations

    GitHub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antibiot
    0.46
     bezier
    0.45
    ܨ
    0.41
    формация
    0.41
    برها
    0.41
     Antibiot
    0.41
     psychotic
    0.41
    کرو
    0.41
     parku
    0.41
     aperiam
    0.40
    POSITIVE LOGITS
     GitHub
    0.79
    GitHub
    0.73
     Github
    0.66
     Git
    0.63
    Github
    0.58
     SSH
    0.58
    Git
    0.57
    SSH
    0.55
     github
    0.55
     GitLab
    0.54
    Act Density 0.068%

    No Known Activations