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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dx
    -0.08
    ¿
    -0.08
    尽管
    -0.07
    דם
    -0.07
    📧
    -0.07
    generated
    -0.07
    version
    -0.07
     mujer
    -0.07
     steer
    -0.07
    person
    -0.07
    POSITIVE LOGITS
     participating
    0.07
     forty
    0.07
    erspective
    0.07
     רי
    0.07
    𬷕
    0.07
     chapters
    0.07
    _RT
    0.07
     Policies
    0.07
    ﭖ
    0.07
     Showing
    0.07
    Act Density 0.021%

    No Known Activations