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

    Neuronpedia

    INDEX
    Explanations

    owner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     M
    -0.53
     F
    -0.52
     of
    -0.50
     Ro
    -0.50
     Far
    -0.49
     Lane
    -0.48
     Al
    -0.47
     Med
    -0.47
     run
    -0.46
     far
    -0.46
    POSITIVE LOGITS
    Hochspringen
    0.88
     Teut
    0.84
     lordship
    0.83
     Philist
    0.83
     ſmall
    0.82
     myſelf
    0.81
     Jefus
    0.81
     parson
    0.80
     poetical
    0.80
     Pyrene
    0.79
    Act Density 0.030%

    No Known Activations