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

    Neuronpedia

    INDEX
    Explanations

    corner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corner
    -2.02
    corner
    -1.60
     corners
    -1.57
     Corner
    -1.45
    Corner
    -1.40
     CORNER
    -1.39
     Corners
    -1.16
     esquina
    -1.06
    corners
    -1.05
    Corners
    -0.87
    POSITIVE LOGITS
     of
    0.76
    ed
    0.74
    er
    0.62
    ing
    0.57
    add
    0.56
    ers
    0.55
    edm
    0.53
    ie
    0.50
    trous
    0.50
    ages
    0.49
    Act Density 0.065%

    No Known Activations