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

    Neuronpedia

    INDEX
    Explanations

    "hurley and"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xavier
    0.61
     اه
    0.50
    avik
    0.49
    荡
    0.49
    iania
    0.48
    illiard
    0.47
    றிய
    0.46
    шко
    0.46
    ز
    0.46
    IGENCE
    0.45
    POSITIVE LOGITS
     distintas
    0.72
     oppression
    0.69
     pathogenesis
    0.65
     repressive
    0.64
    matmul
    0.63
     patriarchal
    0.63
     भागों
    0.62
     deportivas
    0.62
     oppressive
    0.62
     asesinato
    0.62
    Act Density 0.016%

    No Known Activations