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

    Neuronpedia

    INDEX
    Explanations

    hashtags and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dicho
    0.45
     coloc
    0.45
     direito
    0.42
     préd
    0.42
     recorte
    0.42
    詳しくは
    0.41
     Frente
    0.41
     Semantic
    0.40
     conveniently
    0.40
    前
    0.40
    POSITIVE LOGITS
     κοινων
    0.45
    umbled
    0.40
     المست
    0.39
     куль
    0.38
     어떻게
    0.38
     अंकों
    0.37
     एप
    0.37
     giảm
    0.37
    itive
    0.37
    ίσ
    0.36
    Act Density 0.001%

    No Known Activations