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

    Neuronpedia

    INDEX
    Explanations

    life and career biography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.73
    م
    0.70
     to
    0.66
    N
    0.64
    ل
    0.61
    ed
    0.60
    erness
    0.60
    R
    0.58
    Check
    0.58
     can
    0.57
    POSITIVE LOGITS
     aventure
    0.62
     kari
    0.55
     trayectoria
    0.55
     illustrious
    0.54
     eponymous
    0.53
    ชีวิต
    0.51
     жизни
    0.50
    初代
    0.50
    },
    0.49
     unstable
    0.49
    Act Density 0.015%

    No Known Activations