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

    Neuronpedia

    INDEX
    Explanations

    Companies pride themselves

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Micro
    -0.07
    Application
    -0.07
    处方
    -0.07
    .Ag
    -0.07
    Assertion
    -0.07
    Drug
    -0.06
    (Menu
    -0.06
    Chief
    -0.06
    .game
    -0.06
     Coil
    -0.06
    POSITIVE LOGITS
     bombed
    0.08
    近些
    0.06
    נט
    0.06
    eth
    0.06
    ONG
    0.06
     BEEN
    0.06
     arttır
    0.06
    ('-',
    0.06
    ちゃ
    0.06
     southwest
    0.06
    Act Density 0.013%

    No Known Activations