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

    Neuronpedia

    INDEX
    Explanations

    gear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilerin
    -0.09
     Cooperation
    -0.09
     waiver
    -0.09
     cooperation
    -0.08
     отв
    -0.08
     отличается
    -0.08
     сотруднич
    -0.08
     bovendien
    -0.08
    ksi
    -0.08
    .shiro
    -0.08
    POSITIVE LOGITS
     tangent
    0.08
    Ray
    0.08
    ന്ദ
    0.07
     entirely
    0.07
     '
    0.07
     Ford
    0.07
    Ford
    0.07
     rough
    0.07
    <button
    0.07
     ರಸ್ತೆ
    0.07
    Act Density 0.001%

    No Known Activations