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

    Neuronpedia

    INDEX
    Explanations

    with/by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     analys
    -0.07
    Combo
    -0.07
    べ
    -0.07
    Conv
    -0.07
     corridor
    -0.07
    bservice
    -0.07
     overst
    -0.06
    ingles
    -0.06
    :@"%
    -0.06
     compounds
    -0.06
    POSITIVE LOGITS
    0.07
    .Operator
    0.06
    0.06
     Berg
    0.06
    UP
    0.06
    _section
    0.06
    _WARNINGS
    0.06
     Affero
    0.06
    uni
    0.06
    .FixedSingle
    0.06
    Act Density 0.026%

    No Known Activations