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

    Neuronpedia

    INDEX
    Explanations

    beauty and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒂
    0.44
    bitflag
    0.42
    gover
    0.39
    popular
    0.38
    usermodel
    0.37
    yesi
    0.37
     diffusive
    0.37
    ঙ্গের
    0.36
    桻
    0.36
    carried
    0.36
    POSITIVE LOGITS
    Si
    0.39
     Hr
    0.38
     Selección
    0.38
     பு
    0.38
    Feet
    0.38
     Webb
    0.38
     Ting
    0.38
     hr
    0.37
     Valle
    0.37
    Fi
    0.37
    Act Density 0.001%

    No Known Activations