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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faudra
    -0.09
     prendra
    -0.08
     必
    -0.08
     sampai
    -0.08
     garantir
    -0.08
    ，需要
    -0.08
    േണ്ട
    -0.08
    MODE
    -0.08
    需要
    -0.07
     attachments
    -0.07
    POSITIVE LOGITS
     reminiscent
    0.09
     Neither
    0.09
     suggest
    0.08
     suggesting
    0.08
     neither
    0.08
     initials
    0.08
     राशि
    0.08
    Neither
    0.08
     patrones
    0.08
     strangely
    0.08
    Act Density 0.050%

    No Known Activations