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

    Neuronpedia

    INDEX
    Explanations

    configuration and boolean settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     систем
    0.46
    മില്ല
    0.40
    Req
    0.39
    否定
    0.38
     எதிர்ப்பு
    0.37
     systemic
    0.37
    دأ
    0.36
    default
    0.36
    স্ফ
    0.36
    ("**
    0.36
    POSITIVE LOGITS
     json
    0.47
     gson
    0.45
    json
    0.45
     Json
    0.44
     JSON
    0.44
     JsonConvert
    0.44
    úz
    0.40
    JSON
    0.39
    wand
    0.38
    Json
    0.37
    Act Density 0.004%

    No Known Activations