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

    Neuronpedia

    INDEX
    Explanations

    -score

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diret
    -0.07
    ция
    -0.07
    coes
    -0.07
     Đo
    -0.07
     техничес
    -0.06
     Tob
    -0.06
     Tos
    -0.06
     steak
    -0.06
     niños
    -0.06
     progression
    -0.06
    POSITIVE LOGITS
    make
    0.07
     Hopefully
    0.07
    ======
    0.06
     whatever
    0.06
    angular
    0.06
    <>↵
    0.06
     -----↵
    0.06
    prefer
    0.06
    approximately
    0.06
     asks
    0.06
    Act Density 0.000%

    No Known Activations