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

    Neuronpedia

    INDEX
    Explanations

    reversing words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дин
    0.45
     as
    0.43
     पृष्ठभूमि
    0.42
     Lamb
    0.42
     amplification
    0.40
     selección
    0.40
    كما
    0.40
    द
    0.40
     background
    0.39
     Esperanza
    0.39
    POSITIVE LOGITS
    níku
    0.46
    t
    0.46
    োসিয়ে
    0.44
    isBlank
    0.44
     handled
    0.44
    obtenir
    0.43
    lid
    0.42
     ഞാൻ
    0.42
    ananti
    0.42
    noon
    0.42
    Act Density 0.006%

    No Known Activations