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
     asiat
    -0.07
    Messages
    -0.07
    Recognition
    -0.07
     unborn
    -0.06
    -element
    -0.06
    ItemList
    -0.06
    weapons
    -0.06
    ENC
    -0.06
    vinc
    -0.06
    ole
    -0.06
    POSITIVE LOGITS
     इतन
    0.07
    iske
    0.06
     اجازه
    0.06
     Ragnar
    0.06
     обмеж
    0.06
    ための
    0.06
     επίσης
    0.06
     Shake
    0.06
     위해
    0.06
    �
    0.06
    Act Density 0.008%

    No Known Activations