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

    Neuronpedia

    INDEX
    Explanations

    science fiction and center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σταση
    0.47
    smittel
    0.44
     závod
    0.43
    isière
    0.43
     %@",
    0.43
     \"%
    0.42
     счита
    0.41
    ódigo
    0.41
     onlyOwner
    0.40
    سم
    0.40
    POSITIVE LOGITS
     science
    0.95
     Scientists
    0.90
     ciencia
    0.87
     Science
    0.87
    Scientists
    0.86
     scientists
    0.85
     scientist
    0.83
    Scient
    0.80
     ciência
    0.80
     scientific
    0.80
    Act Density 0.012%

    No Known Activations