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

    Neuronpedia

    INDEX
    Explanations

    expansionism, living space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.98
     compuestos
    0.90
     colocar
    0.88
    Habitat
    0.86
    Venezuela
    0.85
    Sub
    0.84
    ación
    0.84
    તમ
    0.84
     эти
    0.83
    なりません
    0.83
    POSITIVE LOGITS
     bears
    0.73
     যাবত
    0.73
     DOF
    0.70
     handles
    0.70
     Ej
    0.69
    埜
    0.68
     Figs
    0.68
     vo
    0.67
     BUT
    0.66
    вано
    0.66
    Act Density 0.001%

    No Known Activations