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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nt
    -0.07
    -loving
    -0.07
     hawk
    -0.07
    .Clock
    -0.06
     McInt
    -0.06
     Mall
    -0.06
     Getting
    -0.06
    (requestCode
    -0.06
     challenging
    -0.06
    .exclude
    -0.06
    POSITIVE LOGITS
     '=
    0.08
    бі
    0.07
    -www
    0.07
     Emails
    0.06
    /alert
    0.06
    _OBS
    0.06
    'post
    0.06
     ابو
    0.06
     الولايات
    0.06
     pageInfo
    0.06
    Act Density 0.006%

    No Known Activations