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

    Neuronpedia

    INDEX
    Explanations

    Emphasis words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     목소
    -0.07
    ुआ
    -0.06
    娜
    -0.06
     RADIO
    -0.06
    .Static
    -0.06
    onth
    -0.06
     각각
    -0.06
     قدرت
    -0.06
    +/
    -0.06
     dấu
    -0.06
    POSITIVE LOGITS
     innate
    0.06
    Insert
    0.06
     nữa
    0.06
    ）的
    0.06
     weer
    0.06
     prayed
    0.06
     spring
    0.06
     Scarlett
    0.06
     pad
    0.06
    藍
    0.06
    Act Density 0.030%

    No Known Activations