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

    Neuronpedia

    INDEX
    Explanations

    realization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     destructive
    -0.07
     survived
    -0.07
     النظام
    -0.07
    istung
    -0.07
    .Resources
    -0.06
    党
    -0.06
     duro
    -0.06
     دش
    -0.06
    ुष
    -0.06
     poder
    -0.06
    POSITIVE LOGITS
    �
    0.07
    /reference
    0.07
    jdbc
    0.07
    acters
    0.06
    ETA
    0.06
    )):↵
    0.06
     pygame
    0.06
    〈
    0.06
    -М
    0.06
    Url
    0.06
    Act Density 0.000%

    No Known Activations