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

    Neuronpedia

    INDEX
    Explanations

    **(leaf sheaths)**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .”
    0.36
     sections
    0.33
     jol
    0.33
     polarization
    0.33
     carro
    0.33
     Addison
    0.32
    ,”
    0.32
    。”
    0.32
    .’
    0.31
     comenzó
    0.31
    POSITIVE LOGITS
     Krank
    0.32
    蟀
    0.32
     postulated
    0.30
     favours
    0.30
    იდ
    0.30
    BC
    0.30
    হৃত
    0.30
    ruits
    0.29
    steins
    0.29
    ỗ
    0.29
    Act Density 0.001%

    No Known Activations