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

    Neuronpedia

    INDEX
    Explanations

    correction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Svět
    -0.07
    哭
    -0.07
    _mirror
    -0.06
     pieces
    -0.06
     cancelling
    -0.06
     finalized
    -0.06
    èn
    -0.06
    drink
    -0.06
    شركة
    -0.06
     solder
    -0.06
    POSITIVE LOGITS
     Gaza
    0.06
     disclosures
    0.06
    hap
    0.06
     Yap
    0.06
     Otto
    0.06
    osemite
    0.06
     Teresa
    0.06
     Orlando
    0.06
     LIS
    0.06
    /↵↵↵↵
    0.06
    Act Density 0.015%

    No Known Activations