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

    Neuronpedia

    INDEX
    Explanations

    bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     degeneracy
    0.22
    😿
    0.21
     hadron
    0.20
    StartIndex
    0.19
     sovere
    0.19
    Cols
    0.19
    graphHead
    0.18
     explosions
    0.18
     heuristics
    0.18
     anarchy
    0.18
    POSITIVE LOGITS
    า
    0.23
    ina
    0.22
    ada
    0.21
    ado
    0.21
    ı
    0.21
    ovan
    0.21
    oma
    0.21
     a
    0.21
     यह
    0.20
    也就是说
    0.20
    Act Density 0.436%

    No Known Activations