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

    Neuronpedia

    INDEX
    Explanations

    Spring framework modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     downhill
    0.40
    ченной
    0.40
     sparring
    0.39
     Elektrokhimiya
    0.38
    AMPLE
    0.38
     dryers
    0.38
     gasped
    0.38
     Balashov
    0.37
     magnetite
    0.37
    锉
    0.37
    POSITIVE LOGITS
    stereotype
    0.98
    boot
    0.81
    beans
    0.75
    scheduling
    0.73
    http
    0.66
    stere
    0.65
    context
    0.64
    Stere
    0.64
     boot
    0.63
    stereo
    0.61
    Act Density 0.000%

    No Known Activations