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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cp
    -0.07
    _dist
    -0.06
    ,node
    -0.06
     Zig
    -0.06
     saison
    -0.06
     displacement
    -0.06
    дол
    -0.06
     dof
    -0.06
    组织领导
    -0.06
     giú
    -0.06
    POSITIVE LOGITS
     Plate
    0.07
    .TYPE
    0.07
    掛
    0.07
    IMARY
    0.06
    時の
    0.06
    flowers
    0.06
    apo
    0.06
    묭
    0.06
    帼
    0.06
    �
    0.06
    Act Density 0.181%

    No Known Activations