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

    Neuronpedia

    INDEX
    Explanations

    configuration and setup files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Baiklah
    0.40
    Pil
    0.39
     hozzá
    0.38
     úlo
    0.38
    Steph
    0.38
    摆
    0.37
     Sash
    0.36
    rotl
    0.36
    ceğini
    0.36
     Stephan
    0.35
    POSITIVE LOGITS
     rules
    0.45
    配置文件
    0.44
     RULES
    0.43
    config
    0.41
     manifesto
    0.40
     exclusions
    0.40
     prays
    0.40
     parameters
    0.39
     characteristics
    0.39
     configuration
    0.39
    Act Density 0.003%

    No Known Activations