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

    Neuronpedia

    INDEX
    Explanations

    templates and code insertion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उर्वर
    0.41
    wilderness
    0.40
    erdale
    0.39
     رد
    0.38
     उर्व
    0.37
     mildly
    0.37
    MUR
    0.37
    ாலம்
    0.37
     saucer
    0.36
    udier
    0.36
    POSITIVE LOGITS
     Templates
    0.98
     templates
    0.89
     template
    0.86
     Template
    0.86
    Templates
    0.75
    模板
    0.74
    template
    0.72
    Template
    0.71
    templates
    0.67
     шабло
    0.63
    Act Density 0.004%

    No Known Activations