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

    Neuronpedia

    INDEX
    Explanations

    font

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directing
    -0.07
     Presidents
    -0.07
    IME
    -0.06
     mystery
    -0.06
     Recru
    -0.06
     clay
    -0.06
     ряд
    -0.06
    emory
    -0.06
     соответств
    -0.06
     NULL
    -0.06
    POSITIVE LOGITS
    (codec
    0.07
    irq
    0.07
    .mongodb
    0.07
    ládá
    0.06
     guerr
    0.06
     вида
    0.06
    ******
↵
    0.06
    eşit
    0.06
    spots
    0.06
     přítom
    0.06
    Act Density 0.004%

    No Known Activations