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

    Neuronpedia

    INDEX
    Explanations

    say "open" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bitmap
    -0.07
     farklı
    -0.06
     Orion
    -0.06
     Attributes
    -0.06
     понять
    -0.06
     recycled
    -0.06
     نوفمبر
    -0.06
    hello
    -0.06
    etr
    -0.06
    _BINARY
    -0.06
    POSITIVE LOGITS
     cong
    0.07
     crafts
    0.07
     puan
    0.06
     eff
    0.06
     toplantı
    0.06
     discontent
    0.06
     берег
    0.06
    nis
    0.06
    "]));↵
    0.06
     PCIe
    0.06
    Act Density 0.268%

    No Known Activations