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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curso
    -0.07
    双腿
    -0.07
    agem
    -0.07
     Anderson
    -0.06
     весьма
    -0.06
    很是
    -0.06
     ngo
    -0.06
    נהג
    -0.06
     foi
    -0.06
     Coffee
    -0.06
    POSITIVE LOGITS
     Disc
    0.07
    _SAMPL
    0.06
     우리의
    0.06
    "><?
    0.06
     mechan
    0.06
    キュ
    0.06
    Assembler
    0.06
    オリジ
    0.06
    _stat
    0.06
    >B
    0.06
    Act Density 0.007%

    No Known Activations