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

    Neuronpedia

    INDEX
    Explanations

    Code/Latex snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CI
    -0.07
     deadliest
    -0.07
     CAD
    -0.06
     exposes
    -0.06
     jig
    -0.06
    إن
    -0.06
    _AC
    -0.06
     Courts
    -0.06
     worst
    -0.06
    death
    -0.06
    POSITIVE LOGITS
     nett
    0.07
    _audio
    0.06
    aq
    0.06
    loat
    0.06
    -tech
    0.06
     допомаг
    0.06
     coherence
    0.06
    0.06
    thag
    0.06
    ávání
    0.06
    Act Density 0.000%

    No Known Activations