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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document structure commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙧
    0.44
    ן
    0.42
    𝗿
    0.41
    ช่วง
    0.40
    ꔰ
    0.40
    𝘥
    0.39
     рука
    0.38
     विभिन्न
    0.38
    踮
    0.38
    ⓪
    0.38
    POSITIVE LOGITS
    4
    0.47
     technologies
    0.42
    _
    0.39
     should
    0.37
     implementations
    0.36
    8
    0.36
    Ign
    0.35
    5
    0.35
    9
    0.35
    0.35
    Act Density 0.001%

    No Known Activations