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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACC
    -0.07
    Ê
    -0.06
     Harrison
    -0.06
    Passed
    -0.06
    чно
    -0.06
    echan
    -0.06
     "\",
    -0.06
     Identify
    -0.06
     Laure
    -0.06
     Provincial
    -0.06
    POSITIVE LOGITS
    Uh
    0.07
     lname
    0.07
     آق
    0.07
     mos
    0.06
    596
    0.06
     सन
    0.06
    turn
    0.06
    Unknown
    0.06
     asia
    0.06
    embed
    0.06
    Act Density 0.000%

    No Known Activations