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

    Neuronpedia

    INDEX
    Explanations

    Mixed content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _every
    -0.06
    ，然后
    -0.06
    .loop
    -0.06
     FW
    -0.06
     Серг
    -0.06
    ctr
    -0.06
     stocked
    -0.06
     capitalists
    -0.06
    奶
    -0.06
    olor
    -0.06
    POSITIVE LOGITS
     orthogonal
    0.07
    가
    0.07
     Nevada
    0.06
    τον
    0.06
    _Items
    0.06
     flute
    0.06
    UpDown
    0.06
     bers
    0.06
    200
    0.06
    (ierr
    0.06
    Act Density 0.000%

    No Known Activations