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

    Neuronpedia

    INDEX
    Explanations

    orean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inferred
    -0.07
    late
    -0.07
    cies
    -0.06
    dık
    -0.06
    นะ
    -0.06
    .FALSE
    -0.06
    (PC
    -0.06
     Το
    -0.06
     '['
    -0.06
     anomalies
    -0.05
    POSITIVE LOGITS
    turn
    0.08
    Directories
    0.07
     getRandom
    0.06
     необходим
    0.06
     Turn
    0.06
    WE
    0.06
    Wild
    0.06
    vendor
    0.06
     返回
    0.06
     transfer
    0.06
    Act Density 0.001%

    No Known Activations