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

    Neuronpedia

    INDEX
    Explanations

    computer code and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dst
    -0.07
     日期
    -0.07
     мол
    -0.07
    なんて
    -0.06
     Shak
    -0.06
     봐
    -0.06
    Pitch
    -0.06
     хорошо
    -0.06
     Saul
    -0.06
     proudly
    -0.06
    POSITIVE LOGITS
    _interface
    0.08
     recommendation
    0.07
    -bearing
    0.07
    KS
    0.07
     conjunction
    0.06
    actice
    0.06
    เว
    0.06
     getObject
    0.06
    -support
    0.06
    rud
    0.06
    Act Density 0.002%

    No Known Activations