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

    Neuronpedia

    INDEX
    Explanations

    philosophical and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ่น
    0.48
    ëlle
    0.46
     专业
    0.46
     եւ
    0.45
    etur
    0.45
    iment
    0.44
    ρών
    0.44
    nên
    0.43
     token
    0.42
     μπορεί
    0.42
    POSITIVE LOGITS
    Dok
    0.51
    ガン
    0.49
     concluding
    0.49
    Pow
    0.48
    Pr
    0.47
    Produkt
    0.47
    vict
    0.47
     starke
    0.46
    Ä
    0.46
     लिं
    0.46
    Act Density 0.000%

    No Known Activations