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

    Neuronpedia

    INDEX
    Explanations

    click here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تكون
    0.87
     }(\
    0.82
    كون
    0.82
    idone
    0.80
    以
    0.80
    umuz
    0.79
    کیا
    0.78
    sse
    0.77
     рассказыва
    0.77
    邺
    0.77
    POSITIVE LOGITS
    bait
    1.35
     heels
    1.26
    dokter
    1.14
     anywhere
    1.14
     hereto
    1.05
     tombol
    1.03
     nbfs
    1.03
     einmal
    1.00
    )="
    0.97
     buttons
    0.97
    Act Density 0.028%

    No Known Activations