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

    Neuronpedia

    INDEX
    Explanations

    split

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ूं
    -0.07
    -wing
    -0.07
     Abe
    -0.07
    adní
    -0.07
     purse
    -0.07
    _confirmation
    -0.07
    sty
    -0.07
    .slot
    -0.07
    랜
    -0.06
     desk
    -0.06
    POSITIVE LOGITS
     Attendance
    0.06
     em
    0.06
     FileReader
    0.06
    .setMessage
    0.06
     ص
    0.06
     PIO
    0.06
    Processes
    0.06
    corr
    0.06
    Attendance
    0.06
    kers
    0.06
    Act Density 0.003%

    No Known Activations