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

    Neuronpedia

    INDEX
    Explanations

    su

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tối
    -0.07
    {text
    -0.07
     çab
    -0.06
     nom
    -0.06
    (rp
    -0.06
    _semaphore
    -0.06
    ▋
    -0.06
    _EL
    -0.06
    
    -0.06
    avra
    -0.06
    POSITIVE LOGITS
     Jiang
    0.13
    iang
    0.10
    江
    0.09
     江
    0.08
    '}↵↵
    0.07
    .Customer
    0.07
     inconsistencies
    0.07
    ‚
    0.07
    istle
    0.06
    -child
    0.06
    Act Density 0.006%

    No Known Activations