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

    Neuronpedia

    INDEX
    Explanations

    place names and travelers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vibration
    0.77
     diverse
    0.77
     cis
    0.76
    いる
    0.75
     tangible
    0.75
     sli
    0.74
     cach
    0.74
     der
    0.73
     derivative
    0.73
     potential
    0.72
    POSITIVE LOGITS
    اء
    0.94
    ophilia
    0.90
    rients
    0.89
    psies
    0.89
     angrily
    0.88
    साइट
    0.88
    私たち
    0.87
     って
    0.87
     えっ
    0.86
    vió
    0.84
    Act Density 0.000%

    No Known Activations