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

    Neuronpedia

    INDEX
    Explanations

    combination of both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Second
    0.44
    Sebelum
    0.42
    が一
    0.39
    苾
    0.39
    Pron
    0.38
    Protection
    0.38
    Matching
    0.37
    Petition
    0.37
     previewBuilder
    0.37
    Timer
    0.37
    POSITIVE LOGITS
     keduanya
    0.63
     thereof
    0.60
     दोनों
    0.57
     Beide
    0.56
    两者
    0.55
     both
    0.55
     둘
    0.54
     beide
    0.54
     Ambos
    0.54
     mix
    0.51
    Act Density 0.001%

    No Known Activations