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

    Neuronpedia

    INDEX
    Explanations

    spaceships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horsepower
    -0.07
    undred
    -0.07
     ($("#
    -0.07
    NFL
    -0.07
    aware
    -0.07
    double
    -0.06
    ayment
    -0.06
    COR
    -0.06
     ball
    -0.06
     Persons
    -0.06
    POSITIVE LOGITS
    .fastjson
    0.07
    =a
    0.07
    вен
    0.07
    .TrimSpace
    0.07
     seminal
    0.07
    ssa
    0.06
    :t
    0.06
     허
    0.06
    xFB
    0.06
    ẫu
    0.06
    Act Density 0.049%

    No Known Activations