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

    Neuronpedia

    INDEX
    Explanations

    data and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     máu
    0.45
     ayudarte
    0.45
     EditText
    0.44
     деву
    0.44
     wallpapers
    0.43
     erythrocytes
    0.43
     guerras
    0.43
     mysql
    0.42
     sanguí
    0.42
     atleta
    0.42
    POSITIVE LOGITS
    Don
    0.44
    iaux
    0.43
    Prime
    0.43
    Historically
    0.42
    Three
    0.42
    hav
    0.42
    fi
    0.42
    ti
    0.41
    Optional
    0.41
    och
    0.40
    Act Density 0.000%

    No Known Activations