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

    Neuronpedia

    INDEX
    Explanations

    launching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smiling
    -0.07
     marché
    -0.07
     terrain
    -0.07
     Ripple
    -0.07
     języ
    -0.07
     المادة
    -0.07
    ┩
    -0.07
    inality
    -0.07
    梳理
    -0.07
     Nigeria
    -0.07
    POSITIVE LOGITS
    0.07
    0.07
    حظ
    0.07
    也让
    0.07
    “Oh
    0.07
    pons
    0.07
    (vs
    0.07
    0.06
    礼品
    0.06
    假期
    0.06
    Act Density 0.001%

    No Known Activations