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

    Neuronpedia

    INDEX
    Explanations

    prepositions "from", "of"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HEY
    -0.07
     май
    -0.06
    PROCESS
    -0.06
    okud
    -0.06
     rely
    -0.06
    ceso
    -0.06
     groceries
    -0.06
     Sans
    -0.06
    _FF
    -0.06
    wk
    -0.06
    POSITIVE LOGITS
     loved
    0.06
    reements
    0.06
     Vanguard
    0.06
     NAND
    0.06
     специалист
    0.06
    (selected
    0.06
     يمكن
    0.06
     impartial
    0.06
    .awt
    0.06
     inert
    0.06
    Act Density 0.038%

    No Known Activations