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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (G
    -0.07
    550
    -0.07
    Congratulations
    -0.07
     cryptocurrency
    -0.07
    媒体
    -0.06
    067
    -0.06
    babel
    -0.06
    -established
    -0.06
    alue
    -0.06
    值
    -0.06
    POSITIVE LOGITS
     logfile
    0.06
    사가
    0.06
     McL
    0.06
     csrf
    0.06
     textbox
    0.06
     Train
    0.06
     electorate
    0.06
     سعود
    0.06
     masking
    0.06
     carne
    0.06
    Act Density 0.021%

    No Known Activations