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

    Neuronpedia

    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xz
    -0.07
    Nib
    -0.06
     flex
    -0.06
     XII
    -0.06
     ingenious
    -0.06
    iu
    -0.06
     lux
    -0.06
     Cu
    -0.06
     dzi
    -0.06
    -0.06
    POSITIVE LOGITS
     report
    0.17
     Report
    0.15
    report
    0.15
    Report
    0.14
     reports
    0.13
    reports
    0.12
    .report
    0.12
     reporting
    0.11
    	report
    0.11
     Reports
    0.11
    Act Density 0.040%

    No Known Activations