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

    Neuronpedia

    INDEX
    Explanations

    Sure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pij
    -0.08
    旆
    -0.07
     Omar
    -0.07
     Ils
    -0.07
    נצח
    -0.07
    dhcp
    -0.07
     blinking
    -0.07
     ethereum
    -0.07
     catalogs
    -0.07
     Nicolas
    -0.07
    POSITIVE LOGITS
     canned
    0.07
    _sd
    0.07
    した
    0.07
    不予
    0.07
     код
    0.07
    轻易
    0.07
    hand
    0.06
    -note
    0.06
    務
    0.06
    cott
    0.06
    Act Density 0.020%

    No Known Activations