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

    Neuronpedia

    INDEX
    Explanations

    Direction/Movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.63
    :✨
    -0.52
     esetén
    -0.50
     alike
    -0.49
     متعلقه
    -0.49
    digkeit
    -0.49
     miatt
    -0.48
    .
    -0.47
    exitRule
    -0.45
     kautta
    -0.45
    POSITIVE LOGITS
     myſelf
    0.66
     ſtate
    0.66
    addPreferredGap
    0.62
     faſt
    0.62
     auffi
    0.61
     ſeveral
    0.60
     uſe
    0.60
    bodies
    0.59
     whoſe
    0.59
    ArgsConstructor
    0.58
    Act Density 0.188%

    No Known Activations