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

    Neuronpedia

    INDEX
    Explanations

    end of list or code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    1.14
    और
    0.91
    <unused2110>
    0.91
     aad
    0.89
    その
    0.88
     Somit
    0.88
     Dirección
    0.86
    abhavena
    0.84
    𝐚
    0.84
    <unused512>
    0.83
    POSITIVE LOGITS
    0
    1.16
    4
    1.09
    6
    1.09
    3
    0.98
    </strong>
    0.98
    7
    0.98
    8
    0.95
    9
    0.94
    .
    0.93
    ara
    0.90
    Act Density 0.633%

    No Known Activations