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

    Neuronpedia

    INDEX
    Explanations

    code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MAIN
    -0.06
    +h
    -0.06
     Magn
    -0.06
    B
    -0.06
    …↵
    -0.06
     formats
    -0.06
    <tr
    -0.06
    Ш
    -0.06
    اول
    -0.06
     Ch
    -0.06
    POSITIVE LOGITS
    usalem
    0.07
     Famil
    0.07
    apache
    0.06
    子の
    0.06
     ώρα
    0.06
    $o
    0.06
     \
    0.06
     make
    0.06
     side
    0.06
     tích
    0.06
    Act Density 0.032%

    No Known Activations