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

    Neuronpedia

    INDEX
    Explanations

    non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     katth
    0.47
     Rech
    0.47
     Hayashi
    0.47
     izd
    0.46
     sabit
    0.46
    ですか
    0.45
    branchNode
    0.45
    PlatformTarget
    0.44
     Peki
    0.44
    သောအ
    0.44
    POSITIVE LOGITS
    בו
    0.43
    ،
    0.41
    련
    0.39
    సీ
    0.39
     схемы
    0.39
    руются
    0.38
     конкре
    0.37
     ща
    0.37
     CZ
    0.37
    其实
    0.36
    Act Density 0.024%

    No Known Activations