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

    Neuronpedia

    INDEX
    Explanations

    down to the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \%),
    0.36
    নারায়ণ
    0.35
     Foy
    0.34
    στά
    0.34
    नामेंट
    0.33
    WCHAR
    0.33
    ቾ
    0.33
    τός
    0.32
    क़्त
    0.32
    ጬ
    0.32
    POSITIVE LOGITS
    #
    0.39
     #
    0.37
    brain
    0.36
     ab
    0.32
    0.31
     brain
    0.30
    $
    0.30
    ction
    0.29
                          
    0.29
    #(
    0.29
    Act Density 0.000%

    No Known Activations