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

    Neuronpedia

    INDEX
    Explanations

    cat emojis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addons
    0.55
     enhancements
    0.55
     horarios
    0.55
     azimuth
    0.54
     resellers
    0.54
     licences
    0.54
     quotas
    0.54
     jeopard
    0.53
     journeys
    0.53
     uptime
    0.53
    POSITIVE LOGITS
    0
    0.82
    0.70
    ↵↵
    0.66
    O
    0.64
    he
    0.61
    ing
    0.59
    3
    0.59
    ama
    0.57
    ota
    0.56
    ash
    0.56
    Act Density 0.203%

    No Known Activations