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

    Neuronpedia

    INDEX
    Explanations

    compound distance roots average

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    作る
    0.39
    소년
    0.39
    CLOCK
    0.38
    IQR
    0.38
     नकार
    0.37
     disseminating
    0.37
    ectomy
    0.37
    ISTS
    0.37
     upto
    0.37
    bleshooting
    0.37
    POSITIVE LOGITS
     Essex
    0.43
     вре
    0.40
     retra
    0.39
     Harlem
    0.38
     spir
    0.37
    стройка
    0.37
     상황
    0.37
    טו
    0.37
     }(\
    0.37
    iesią
    0.37
    Act Density 0.004%

    No Known Activations