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

    Neuronpedia

    INDEX
    Explanations

    viewport width attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ുടെ
    1.00
    ptic
    0.99
     YoY
    0.99
     windings
    0.96
    aked
    0.93
     Č
    0.93
     assassin
    0.92
    MOT
    0.91
    antation
    0.91
    ant
    0.90
    POSITIVE LOGITS
    يا
    1.29
     freuen
    1.15
    และความ
    1.09
    ،
    1.09
     της
    1.06
     ও
    1.05
    새
    1.05
    ここ
    1.02
    и
    1.02
    До
    1.01
    Act Density 0.007%

    No Known Activations