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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myself
    -1.31
    myself
    -0.96
    دانشنامهٔ
    -0.95
     myſelf
    -0.94
    expandindo
    -0.90
     meines
    -0.86
     my
    -0.86
    my
    -0.85
     mijn
    -0.85
     meiner
    -0.85
    POSITIVE LOGITS
     System
    0.48
    qrstuvwxyz
    0.45
    gettyimages
    0.44
    criptors
    0.43
    kezett
    0.43
     V
    0.42
    JoinTable
    0.42
     Ver
    0.41
     sys
    0.41
    asily
    0.41
    Act Density 0.022%

    No Known Activations