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

    Neuronpedia

    INDEX
    Explanations

    Assembly contexts in programming and AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uffer
    0.45
     Kalamazoo
    0.39
     cent
    0.38
     பேச
    0.37
     familiar
    0.36
    becomes
    0.36
    gin
    0.36
     جوا
    0.36
    lebih
    0.35
    peč
    0.35
    POSITIVE LOGITS
    Configuration
    0.49
    配置
    0.42
     carbohyd
    0.41
     configurar
    0.41
    Ready
    0.40
    Title
    0.40
    ყენ
    0.39
    Configurations
    0.39
     Configurations
    0.39
    Portale
    0.39
    Act Density 0.000%

    No Known Activations