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

    Neuronpedia

    INDEX
    Explanations

    information reduces entropy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ОО
    0.41
     enlight
    0.40
     Pollution
    0.40
    自家
    0.38
    Gum
    0.37
     monedas
    0.37
    Julia
    0.35
    Loss
    0.35
     firmas
    0.35
     आईपीएस
    0.35
    POSITIVE LOGITS
     savannah
    0.43
    omeres
    0.38
    '',
    0.37
    říklad
    0.37
     ಕ್ಯಾ
    0.37
     parade
    0.37
    wości
    0.37
    žeme
    0.37
     rough
    0.36
    傛
    0.36
    Act Density 0.000%

    No Known Activations