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

    Neuronpedia

    INDEX
    Explanations

    Offering assistance/help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ONEY
    -0.08
     ninete
    -0.07
     Ker
    -0.07
    �
    -0.07
    iton
    -0.07
    umba
    -0.07
    tics
    -0.06
    ylko
    -0.06
     Magnet
    -0.06
     говор
    -0.06
    POSITIVE LOGITS
     correspondence
    0.07
     Resorts
    0.06
     corporations
    0.06
     vested
    0.06
    UNIT
    0.06
    operator
    0.06
    -react
    0.06
    problem
    0.06
     Playlist
    0.06
     facts
    0.06
    Act Density 0.055%

    No Known Activations