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

    Neuronpedia

    INDEX
    Explanations

    acronyms and initialisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.37
     государ
    0.37
     तत्कालीन
    0.36
     Conselho
    0.36
     siglas
    0.35
     denotes
    0.34
     তৎকালীন
    0.34
     그
    0.33
    अभ
    0.33
    통령
    0.33
    POSITIVE LOGITS
    Ave
    0.38
    ry
    0.36
    穸
    0.35
    Pod
    0.35
    上面
    0.34
    Prote
    0.34
    Ji
    0.34
    ove
    0.33
    Pred
    0.33
    হইতে
    0.33
    Act Density 0.014%

    No Known Activations