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

    Neuronpedia

    INDEX
    Explanations

    locations and schools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     particles
    -0.09
     particle
    -0.08
    estro
    -0.07
    particle
    -0.07
    forming
    -0.07
     Particle
    -0.07
    ेश्य
    -0.07
     layouts
    -0.07
    粒
    -0.07
     ±
    -0.07
    POSITIVE LOGITS
    .until
    0.10
     tẹlẹ
    0.08
     bali
    0.08
     beforehand
    0.08
    த்தை
    0.08
     fos
    0.08
     inda
    0.08
    ாவில்
    0.08
    <Vec
    0.08
    (dispatch
    0.08
    Act Density 0.128%

    No Known Activations