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

    Neuronpedia

    INDEX
    Explanations

    closing HTML/JSON structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nio
    0.76
     quanto
    0.76
     unlike
    0.71
     flore
    0.70
     joy
    0.68
     অ
    0.68
    യെ
    0.66
    _{-}^{
    0.65
     reflex
    0.65
     bagian
    0.65
    POSITIVE LOGITS
    """)
    0.97
     йөкләү
    0.91
    "])
    0.89
    ）」
    0.87
    0.84
    </h6>
    0.84
    ”)
    0.83
    》
    0.82
     Hod
    0.82
    "]}
    0.81
    Act Density 0.120%

    No Known Activations