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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    確實
    0.51
    стики
    0.44
     infatti
    0.41
    또한
    0.41
     እንዲሁ
    0.41
    copter
    0.41
     পরিবর্তনের
    0.40
     देखील
    0.39
    ğinin
    0.39
     என்பது
    0.39
    POSITIVE LOGITS
     this
    0.59
     they
    0.53
     kwamba
    0.52
     यह
    0.51
     Tämä
    0.51
     there
    0.50
     هذا
    0.50
     tämä
    0.50
     এই
    0.49
     aceasta
    0.48
    Act Density 0.010%

    No Known Activations