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

    Neuronpedia

    INDEX
    Explanations

    signaling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raj
    -0.07
    放宽
    -0.07
    欣喜
    -0.07
    מינים
    -0.07
    מלחמה
    -0.07
    упить
    -0.06
    _al
    -0.06
     Lift
    -0.06
    .native
    -0.06
    -opening
    -0.06
    POSITIVE LOGITS
    テー�
    0.08
    ㅔ
    0.08
     Objective
    0.07
    這些
    0.07
     signaling
    0.07
    プログラ
    0.07
    Utility
    0.07
    Storyboard
    0.07
     deze
    0.07
     homeschool
    0.07
    Act Density 0.005%

    No Known Activations