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

    Neuronpedia

    INDEX
    Explanations

    matrix and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toque
    0.54
     luminosity
    0.50
     treadmill
    0.49
     mural
    0.48
     dining
    0.48
     formant
    0.48
     gelato
    0.47
     Concerto
    0.46
     dialog
    0.46
     murmur
    0.45
    POSITIVE LOGITS
     αποφ
    0.46
     પ્રકાર
    0.46
     ακ
    0.43
    之间
    0.42
    betriebnahme
    0.41
    萎
    0.41
    决定
    0.41
     хотите
    0.41
     согла
    0.40
    发现
    0.40
    Act Density 0.000%

    No Known Activations