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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nearby
    -0.07
    /current
    -0.06
    ucked
    -0.06
     Current
    -0.06
     Modi
    -0.06
    モン
    -0.06
     Strong
    -0.06
    .Binary
    -0.06
     staffers
    -0.05
    zu
    -0.05
    POSITIVE LOGITS
     innov
    0.07
    ……。
    0.06
     HMS
    0.06
    Public
    0.06
     Hog
    0.06
    (qu
    0.06
    _req
    0.06
     eng
    0.06
     motion
    0.06
    merchant
    0.06
    Act Density 0.066%

    No Known Activations