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

    Neuronpedia

    INDEX
    Explanations

    examples and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    átil
    1.74
    pone
    1.71
    çek
    1.69
    джа
    1.63
    iset
    1.57
    timedelta
    1.57
     issue
    1.53
    فير
    1.52
     вина
    1.51
    ด
    1.49
    POSITIVE LOGITS
    ERC
    1.42
     sampel
    1.37
    Escolh
    1.35
    聞
    1.33
    Licenses
    1.33
     contradiction
    1.31
     Rubi
    1.30
     Consultants
    1.29
    以来
    1.29
     hardness
    1.28
    Act Density 0.006%

    No Known Activations