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

    Neuronpedia

    INDEX
    Explanations

    programming operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innovation
    1.03
     louis
    1.02
     comedy
    0.98
     novelist
    0.98
     innovators
    0.97
     passion
    0.96
     london
    0.93
     novels
    0.93
     novelists
    0.92
     canadian
    0.91
    POSITIVE LOGITS
     propi
    1.00
    中でも
    0.89
    هاز
    0.84
    Peripheral
    0.82
    Radar
    0.81
     związku
    0.80
     Peripheral
    0.80
    =?,
    0.80
    waż
    0.80
     quirúrg
    0.79
    Act Density 0.001%

    No Known Activations