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

    Neuronpedia

    INDEX
    Explanations

    medication dosages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Talking
    -0.07
     Imperial
    -0.06
    Editing
    -0.06
    _cmds
    -0.06
     intimidation
    -0.06
    érica
    -0.06
     Decimal
    -0.06
     ترجم
    -0.06
    perial
    -0.06
     composer
    -0.06
    POSITIVE LOGITS
    SON
    0.06
    ρία
    0.06
     apex
    0.06
     voksen
    0.06
     Newly
    0.06
    selectedIndex
    0.06
     struggled
    0.06
    MAND
    0.06
     `;↵
    0.06
    ALI
    0.06
    Act Density 0.035%

    No Known Activations