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

    Neuronpedia

    INDEX
    Explanations

    research study papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.26
    وم
    0.26
     compartments
    0.25
    $\
    0.25
    дил
    0.24
    ૩
    0.24
    ぐ
    0.23
    אים
    0.23
     transplanted
    0.23
    $.\
    0.23
    POSITIVE LOGITS
    𝒮
    0.28
    <unused236>
    0.27
     Studie
    0.26
     Cine
    0.25
    <unused741>
    0.25
    Charset
    0.25
     Naruto
    0.25
     आल्सो
    0.25
    년
    0.25
    ede
    0.25
    Act Density 0.200%

    No Known Activations