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

    Neuronpedia

    INDEX
    Explanations

    math operations and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Offsets
    0.45
    邰
    0.43
     Landkreis
    0.43
    ograv
    0.42
    Laz
    0.42
    an
    0.41
     Kenneth
    0.41
    oarthritis
    0.41
    oncer
    0.41
    itiers
    0.41
    POSITIVE LOGITS
     geographical
    0.47
    ㅝ
    0.42
     geography
    0.42
     sinus
    0.41
     suboptimal
    0.40
     geographic
    0.39
    geographic
    0.39
     national
    0.38
     vacation
    0.37
    national
    0.37
    Act Density 0.001%

    No Known Activations