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

    Neuronpedia

    INDEX
    Explanations

    di/tri prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Time
    -0.07
    yalty
    -0.07
    -period
    -0.06
    erli
    -0.06
     Forget
    -0.06
     зрост
    -0.06
     Marcos
    -0.06
    areth
    -0.06
     主
    -0.06
    атег
    -0.06
    POSITIVE LOGITS
     Dim
    0.06
     rifle
    0.06
    onDelete
    0.06
    _DIM
    0.06
    kv
    0.06
     minimum
    0.06
    决定
    0.06
    221
    0.06
    >',
    0.06
    (NUM
    0.06
    Act Density 0.030%

    No Known Activations