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

    Neuronpedia

    INDEX
    Explanations

    social media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gradu
    -0.09
     Grad
    -0.08
    _rotation
    -0.08
    .bundle
    -0.08
     Summer
    -0.07
     Ahead
    -0.07
     rotations
    -0.07
     skipping
    -0.07
     பாதுக
    -0.07
     '
    -0.07
    POSITIVE LOGITS
    投诉
    0.12
     dissatisfied
    0.12
     unhappy
    0.11
     शिकायत
    0.11
     പരാത
    0.10
     പരാതി
    0.10
     ફરિયાદ
    0.10
     customer
    0.09
     dissatisfaction
    0.09
     disappointed
    0.09
    Act Density 0.025%

    No Known Activations