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

    Neuronpedia

    INDEX
    Explanations

    in the beginning, inception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⲥ
    0.44
    porcion
    0.42
    javase
    0.41
    ร็จ
    0.39
     taught
    0.39
    FOOT
    0.39
    μορφ
    0.39
    森林
    0.38
     Toni
    0.38
     Venkates
    0.38
    POSITIVE LOGITS
     []:
    0.58
     IN
    0.52
     IR
    0.45
     อิน
    0.44
     inches
    0.44
     regard
    0.40
     club
    0.40
     order
    0.40
     In
    0.39
    िरा
    0.39
    Act Density 0.001%

    No Known Activations