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

    Neuronpedia

    INDEX
    Explanations

    key features and recognizing dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ."
    0.36
    wide
    0.35
    branded
    0.32
     episcop
    0.31
    inthe
    0.31
    !"
    0.31
    錒
    0.31
    ,"
    0.30
    ".
    0.30
    .]
    0.30
    POSITIVE LOGITS
    稃
    0.40
    ﺮ
    0.39
     лет
    0.36
     वर
    0.36
    Lua
    0.36
    т
    0.36
    ي
    0.36
    रह
    0.34
    िजन
    0.34
     famí
    0.33
    Act Density 1.254%

    No Known Activations