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

    Neuronpedia

    INDEX
    Explanations

    Technical writing/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etrize
    -0.07
    lém
    -0.07
    žít
    -0.06
    чини
    -0.06
    Commerce
    -0.06
    isEqualTo
    -0.06
     wł
    -0.06
     rnn
    -0.06
    -tw
    -0.06
    anders
    -0.06
    POSITIVE LOGITS
     спор
    0.07
    .MouseEventHandler
    0.07
    .isAdmin
    0.06
     Wish
    0.06
     missed
    0.06
    _DETAIL
    0.06
     Rosenstein
    0.06
     hollow
    0.06
     MIS
    0.06
    659
    0.06
    Act Density 0.445%

    No Known Activations