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

    Neuronpedia

    INDEX
    Explanations

    fried

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (u
    -0.07
    .Param
    -0.07
    _DECLS
    -0.07
     Naming
    -0.06
     effectiveness
    -0.06
    ucing
    -0.06
     abandonment
    -0.06
    693
    -0.06
    HW
    -0.06
     RTBU
    -0.06
    POSITIVE LOGITS
     fried
    0.07
     집
    0.07
    ิเว
    0.06
     Papua
    0.06
     Trinidad
    0.06
     ngữ
    0.06
    .OrdinalIgnoreCase
    0.06
     pcap
    0.06
     Nederland
    0.06
    .FromSeconds
    0.06
    Act Density 0.009%

    No Known Activations