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

    Neuronpedia

    INDEX
    Explanations

    web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്കൊ
    0.45
    یدہ
    0.43
    اونلو
    0.41
     कंडिशनर
    0.40
    riak
    0.40
     $=\
    0.39
    ²',
    0.39
    ectomy
    0.39
    प्लेस
    0.39
    㞒
    0.38
    POSITIVE LOGITS
    <0xC2>
    0.50
    0.48
      
    0.48
       
    0.46
    ↵
    0.46
     .
    0.42
     or
    0.37
    be
    0.37
     (
    0.36
         
    0.35
    Act Density 0.004%

    No Known Activations