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

    Neuronpedia

    INDEX
    Explanations

    introducing examples or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.62
    е
    0.52
    er
    0.50
     in
    0.47
    の
    0.47
     dentro
    0.46
     an
    0.46
    嶅
    0.46
     kurz
    0.45
     aumentando
    0.45
    POSITIVE LOGITS
    0
    0.40
    मा
    0.38
    पणे
    0.36
    יים
    0.36
    𝒞
    0.35
    持つ
    0.34
    אן
    0.32
    ದುಕೊಳ್ಳ
    0.32
    ง
    0.31
     cuddling
    0.30
    Act Density 0.056%

    No Known Activations