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

    Neuronpedia

    INDEX
    Explanations

    list itemization or code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     எடுத்துக்கா
    0.46
    бли
    0.43
    Arnold
    0.42
     unbek
    0.42
     எடுத்து
    0.40
    allclasses
    0.40
     університету
    0.40
     McCullough
    0.40
    isPartOf
    0.39
    bezpie
    0.39
    POSITIVE LOGITS
     توان
    0.49
     CQG
    0.42
     fungsi
    0.41
     mediation
    0.41
     prototyping
    0.40
     bi
    0.39
     pełni
    0.39
     ino
    0.39
     polymeric
    0.39
     funcion
    0.38
    Act Density 0.000%

    No Known Activations