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

    Neuronpedia

    INDEX
    Explanations

    Please respond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sidelined
    0.84
     emerged
    0.74
     noteworthy
    0.73
     certi
    0.73
     desirable
    0.71
     購入
    0.70
     diagnosed
    0.70
     headquartered
    0.68
    Buyers
    0.68
     énergétique
    0.68
    POSITIVE LOGITS
    Shower
    0.82
    ляют
    0.80
    alih
    0.77
    Sp
    0.76
    いきます
    0.75
    rjust
    0.75
    Heating
    0.75
    сы
    0.74
    чный
    0.74
    bly
    0.74
    Act Density 0.000%

    No Known Activations