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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    miştir
    -0.08
    女人
    -0.08
    October
    -0.07
     और
    -0.07
    -inline
    -0.06
    Houston
    -0.06
     будинку
    -0.06
    ��
    -0.06
    cesso
    -0.06
    ?p
    -0.06
    POSITIVE LOGITS
    /Users
    0.06
    創
    0.06
     generally
    0.06
    imes
    0.06
    ograf
    0.06
     Killer
    0.06
    ASI
    0.06
     Protected
    0.06
     mileage
    0.06
    Ren
    0.06
    Act Density 0.091%

    No Known Activations