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

    Neuronpedia

    INDEX
    Explanations

    mood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     an
    -0.08
     ஒரு
    -0.08
    ுமார்
    -0.08
     a
    -0.08
     नियम
    -0.08
     pauvre
    -0.08
    akwa
    -0.08
     قوان
    -0.07
    mother
    -0.07
     />,
    -0.07
    POSITIVE LOGITS
     novamente
    0.11
     again
    0.10
     nuevamente
    0.10
     Again
    0.10
     reaffirm
    0.10
     reiterated
    0.09
     continuará
    0.09
    новь
    0.09
    Again
    0.09
     erneut
    0.09
    Act Density 0.006%

    No Known Activations