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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     istih
    -0.07
     درآمد
    -0.06
     donc
    -0.06
     carbonate
    -0.06
    Speak
    -0.06
    toBe
    -0.06
    шая
    -0.06
     rebels
    -0.06
    far
    -0.06
    osen
    -0.06
    POSITIVE LOGITS
    "]){↵
    0.07
    '):↵
    0.07
     lim
    0.07
    тю
    0.06
    ิต
    0.06
     타
    0.06
     publisher
    0.06
    leted
    0.06
    roach
    0.06
     amt
    0.06
    Act Density 0.002%

    No Known Activations