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

    Neuronpedia

    INDEX
    Explanations

    close up, fix the, focus on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ann
    5.83
     famille
    5.48
    [*][[
    5.47
     kes
    5.34
     hem
    5.30
     comité
    5.30
     les
    5.26
     gez
    5.26
     Sie
    5.25
     aus
    5.25
    POSITIVE LOGITS
    rinsic
    -0.90
    knię
    -0.92
    6
    -1.12
    7
    -1.14
    หัส
    -1.16
     adimensional
    -1.17
    3
    -1.27
    8
    -1.30
    Civita
    -1.31
     instinctively
    -1.32
    Act Density 0.135%

    No Known Activations