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

    Neuronpedia

    INDEX
    Explanations

    zip files, immunoglobulin, monte carlo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tres
    -0.09
    ൾ
    -0.08
     dex
    -0.08
     Driven
    -0.07
    ള
    -0.07
     prohib
    -0.07
    lassen
    -0.07
    -Clause
    -0.07
     Przy
    -0.07
    ള്
    -0.07
    POSITIVE LOGITS
     என்ற
    0.08
    Rome
    0.08
    setting
    0.07
    verbose
    0.07
     biking
    0.07
     அந்த
    0.07
    otal
    0.07
     yoga
    0.07
    ltr
    0.07
     rewind
    0.07
    Act Density 0.000%

    No Known Activations