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

    Neuronpedia

    INDEX
    Explanations

    3 or 8

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fov
    -0.08
     construed
    -0.07
    uters
    -0.07
     overlooking
    -0.07
     Ron
    -0.07
    其中有
    -0.07
     evoke
    -0.06
     adversaries
    -0.06
    lew
    -0.06
    땠
    -0.06
    POSITIVE LOGITS
    Wiki
    0.08
     grave
    0.07
    功用
    0.07
    _Variable
    0.07
     applic
    0.07
     sentir
    0.07
     были
    0.07
    กฎ
    0.07
    Things
    0.07
    (proto
    0.06
    Act Density 0.013%

    No Known Activations