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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.02
     desist
    0.93
     fascin
    0.90
    ↵↵
    0.89
     /,
    0.83
     *,
    0.81
     instructive
    0.80
     conjectured
    0.80
     fantas
    0.80
    ,【
    0.79
    POSITIVE LOGITS
    5
    1.21
    2
    1.21
    about
    1.20
    by
    1.18
    From
    1.15
    3
    1.13
    around
    1.13
    from
    1.13
    4
    1.12
    -'
    1.12
    Act Density 0.000%

    No Known Activations