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

    Neuronpedia

    INDEX
    Explanations

    Okay, secrets, or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     κατα
    0.59
     участке
    0.52
     διο
    0.52
    াবিশ
    0.51
     donned
    0.51
     macrophage
    0.50
     που
    0.50
     ο
    0.50
    λημα
    0.49
     καλύτε
    0.49
    POSITIVE LOGITS
    labelText
    0.42
    leqslant
    0.41
    bread
    0.41
    coffee
    0.40
    ags
    0.39
    Coffee
    0.38
     ducks
    0.38
    0.38
    ිට
    0.38
    차
    0.37
    Act Density 0.000%

    No Known Activations