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

    Neuronpedia

    INDEX
    Explanations

    rollicking reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eworld
    -0.07
    -Man
    -0.06
    ictureBox
    -0.06
    ділу
    -0.06
    áfico
    -0.06
     postage
    -0.06
     tabletop
    -0.06
    Mission
    -0.06
    strike
    -0.05
    �
    -0.05
    POSITIVE LOGITS
     delightful
    0.07
     sey
    0.07
    nox
    0.07
    .li
    0.07
    .getInput
    0.07
    適用
    0.07
    .band
    0.07
    .top
    0.07
    duit
    0.07
    (album
    0.06
    Act Density 0.008%

    No Known Activations