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

    Neuronpedia

    INDEX
    Explanations

    informing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    賞
    -0.07
    ْه
    -0.07
    chl
    -0.07
    edian
    -0.07
    bral
    -0.06
    -B
    -0.06
    bad
    -0.06
    Opcode
    -0.06
    偷
    -0.06
    _hw
    -0.06
    POSITIVE LOGITS
     REGISTER
    0.06
    IDA
    0.06
     mounted
    0.06
    CHAPTER
    0.06
    ambia
    0.06
     deliberately
    0.06
    GREEN
    0.06
     caution
    0.06
     sever
    0.06
    itespace
    0.06
    Act Density 0.005%

    No Known Activations