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

    Neuronpedia

    INDEX
    Explanations

    sleep and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /-
    0.44
    itars
    0.42
     പറയാ
    0.42
    ORDAN
    0.41
    Depos
    0.39
    俑
    0.39
    Arte
    0.39
     مما
    0.38
    Converters
    0.38
     Treasures
    0.38
    POSITIVE LOGITS
     magnitude
    0.36
     seguente
    0.35
    ）、
    0.35
    자와
    0.35
    চ্ছ
    0.35
     scribe
    0.35
     noma
    0.34
     contacted
    0.34
     Jerome
    0.34
     pays
    0.33
    Act Density 0.000%

    No Known Activations