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

    Neuronpedia

    INDEX
    Explanations

    Unusual character combinations

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     hodnoty
    -0.07
    意义
    -0.07
    láda
    -0.07
    なし
    -0.06
     Pf
    -0.06
    拥有
    -0.06
    iveness
    -0.06
    /static
    -0.06
     Corinthians
    -0.06
     relev
    -0.06
    POSITIVE LOGITS
     Happ
    0.08
    unma
    0.06
    .signup
    0.06
     XmlDocument
    0.06
    rek
    0.06
    pkt
    0.06
    .URL
    0.06
     happiest
    0.06
    ^K
    0.06
    zoom
    0.06
    Act Density 0.000%

    No Known Activations