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

    Neuronpedia

    INDEX
    Explanations

    totality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endemic
    -0.07
    upp
    -0.07
    rok
    -0.06
    Beta
    -0.06
    ombok
    -0.06
     freight
    -0.06
     physical
    -0.06
     structs
    -0.06
     accr
    -0.06
     tractor
    -0.06
    POSITIVE LOGITS
     taky
    0.07
    했습니다
    0.07
    ]:↵↵
    0.07
    `.↵↵
    0.07
     ขาย
    0.06
    Awesome
    0.06
     wykon
    0.06
    !"↵↵
    0.06
    ।
    0.06
    ्यम
    0.06
    Act Density 0.265%

    No Known Activations