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

    Neuronpedia

    INDEX
    Explanations

    hind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apenas
    -0.07
    beat
    -0.07
     Trap
    -0.07
    &oacute
    -0.07
     青
    -0.07
    �乐
    -0.06
     Κύπ
    -0.06
     quần
    -0.06
     reactor
    -0.06
     plural
    -0.06
    POSITIVE LOGITS
     hind
    0.28
     Hind
    0.17
    hind
    0.12
     حکومت
    0.07
     ovarian
    0.06
     диамет
    0.06
    .source
    0.06
    XmlElement
    0.06
    억
    0.06
     obsessive
    0.06
    Act Density 0.001%

    No Known Activations