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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    го
    -0.07
     đã
    -0.06
     TLC
    -0.06
    274
    -0.06
     فرو
    -0.06
    ž
    -0.06
    alarını
    -0.05
     Glyph
    -0.05
     credibility
    -0.05
     incarceration
    -0.05
    POSITIVE LOGITS
    .Horizontal
    0.07
    .setting
    0.07
    slider
    0.07
    anches
    0.07
     Infinite
    0.07
     personal
    0.07
    .va
    0.07
     deed
    0.07
    .Vertical
    0.06
     рух
    0.06
    Act Density 0.300%

    No Known Activations