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

    Neuronpedia

    INDEX
    Explanations

    fouls and illegal contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ασ
    0.45
    猜
    0.44
     பா
    0.43
     humano
    0.43
    icação
    0.41
    羞
    0.40
     εξε
    0.40
    血压
    0.39
     याचा
    0.39
    ação
    0.39
    POSITIVE LOGITS
     nags
    0.40
     medium
    0.37
     conic
    0.37
     streamlined
    0.37
     суу
    0.37
     tulips
    0.36
     chills
    0.36
     streamlines
    0.36
    ଲା
    0.36
    不算
    0.36
    Act Density 0.000%

    No Known Activations