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

    Neuronpedia

    INDEX
    Explanations

    global configuration settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ids
    0.44
     ¼
    0.40
     hunk
    0.38
    )-\
    0.36
    closes
    0.36
     cle
    0.35
     tek
    0.35
    영상
    0.35
     helt
    0.35
     cleans
    0.35
    POSITIVE LOGITS
     Configuration
    0.66
     Configur
    0.64
    配置
    0.62
     配置
    0.60
     configurações
    0.59
     configurar
    0.58
     configuração
    0.58
     Config
    0.57
     defaultConfig
    0.57
     getConfig
    0.56
    Act Density 0.008%

    No Known Activations