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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    갈
    -0.07
    network
    -0.07
    .toByteArray
    -0.07
    (Icons
    -0.07
    pressor
    -0.06
    ва
    -0.06
     spray
    -0.06
    _string
    -0.06
    525
    -0.06
     Lease
    -0.06
    POSITIVE LOGITS
     美
    0.08
     болезни
    0.07
     legacy
    0.06
     conceptual
    0.06
    美
    0.06
    μισ
    0.06
    $tpl
    0.06
     прип
    0.06
    xEB
    0.06
    )-
    0.06
    Act Density 0.007%

    No Known Activations