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

    Neuronpedia

    INDEX
    Explanations

    description and technical details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oirs
    0.46
    ]=-
    0.45
    ͋
    0.45
    lerini
    0.44
     wymien
    0.43
     초기
    0.43
     რომლებიც
    0.42
     Mercier
    0.41
     مرک
    0.41
     znacznie
    0.41
    POSITIVE LOGITS
    Check
    0.51
    Root
    0.49
    Function
    0.46
     check
    0.45
    into
    0.44
    BET
    0.44
    Neut
    0.44
    Mode
    0.44
    Nes
    0.44
     function
    0.43
    Act Density 0.002%

    No Known Activations