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

    Neuronpedia

    INDEX
    Explanations

    Border, manage, sparking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     зарубе
    0.41
     beat
    0.39
     garis
    0.39
     zab
    0.39
     Harmonic
    0.39
     bowl
    0.38
     poucos
    0.38
     bardziej
    0.37
     чого
    0.37
     pastry
    0.37
    POSITIVE LOGITS
    Border
    0.45
    border
    0.44
     $*$
    0.44
    pen
    0.43
    borders
    0.43
    ría
    0.43
    up
    0.42
    leb
    0.42
    branched
    0.42
    ஞ்ஞான
    0.41
    Act Density 0.001%

    No Known Activations