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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्सर
    -0.07
    communications
    -0.06
    tar
    -0.06
     Order
    -0.06
    oplay
    -0.06
     leather
    -0.06
    -ie
    -0.06
    rg
    -0.06
    .bind
    -0.06
    егра
    -0.06
    POSITIVE LOGITS
    办理
    0.07
     Bank
    0.07
    φων
    0.07
    _VARIABLE
    0.07
    ③
    0.06
     desperate
    0.06
    概
    0.06
    			↵			↵
    0.06
    健康
    0.06
     UCLA
    0.06
    Act Density 0.220%

    No Known Activations