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

    Neuronpedia

    INDEX
    Explanations

    likely developments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    珥
    0.48
     Wings
    0.48
     Fu
    0.48
    톄
    0.47
     Poor
    0.46
     Listener
    0.46
     Thatcher
    0.45
     Grover
    0.44
    aii
    0.43
     Poly
    0.43
    POSITIVE LOGITS
    亅
    0.52
    Freel
    0.51
    ][
    0.49
    ".[
    0.49
    JSON
    0.47
    aver
    0.46
    லே
    0.45
     анали
    0.45
    anter
    0.44
     владель
    0.44
    Act Density 0.007%

    No Known Activations