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

    Neuronpedia

    INDEX
    Explanations

    force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ैप
    -0.07
    ═
    -0.06
    EmailAddress
    -0.06
     disorder
    -0.06
    �
    -0.06
     ob
    -0.06
     TG
    -0.06
    igr
    -0.06
    انيا
    -0.06
    IRTH
    -0.06
    POSITIVE LOGITS
     فرض
    0.06
    ！↵
    0.06
     Düz
    0.06
    ROI
    0.06
    anghai
    0.06
    -expanded
    0.06
     REV
    0.06
    gcc
    0.06
     اقدام
    0.06
    (DIR
    0.06
    Act Density 0.008%

    No Known Activations