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

    Neuronpedia

    INDEX
    Explanations

    sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iyel
    -0.07
    (validate
    -0.07
     politics
    -0.07
    amination
    -0.07
    确定
    -0.07
    ähr
    -0.07
     cured
    -0.06
    制作
    -0.06
     tragedies
    -0.06
     righteousness
    -0.06
    POSITIVE LOGITS
     postpone
    0.06
     compliant
    0.06
    ليم
    0.06
     overhead
    0.06
    '});↵
    0.06
     PF
    0.06
    "",
    0.06
     enhancements
    0.06
    ेन
    0.06
    <E
    0.06
    Act Density 0.019%

    No Known Activations