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

    Neuronpedia

    INDEX
    Explanations

    yaml document start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atlantic
    0.45
     Skate
    0.42
     kroner
    0.42
     couro
    0.41
    copies
    0.40
     stocking
    0.40
     Julio
    0.39
    Endpoint
    0.39
     skate
    0.39
     vitamin
    0.38
    POSITIVE LOGITS
     YAML
    0.77
     yaml
    0.68
    Yaml
    0.65
    yaml
    0.65
    YAML
    0.64
    Yam
    0.57
     Yam
    0.54
    配置文件
    0.46
     ---
    0.46
    ('--
    0.46
    Act Density 0.004%

    No Known Activations