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

    Neuronpedia

    INDEX
    Explanations

    lists, JSON, websites, Store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ี
    0.56
    ג
    0.55
     poden
    0.54
    ਲ
    0.54
     spind
    0.52
    𝐧
    0.52
     pesar
    0.50
    ס
    0.50
    𝐞
    0.50
    ז
    0.49
    POSITIVE LOGITS
    0
    0.56
    public
    0.51
     websites
    0.50
     Public
    0.50
    ...”
    0.49
    ...">
    0.48
     Website
    0.47
    …”
    0.46
    2
    0.46
     JSON
    0.46
    Act Density 0.266%

    No Known Activations