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

    Neuronpedia

    INDEX
    Explanations

    options, Shopify, active, TOT, Good morning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dern
    0.52
    uder
    0.51
    uncur
    0.51
    criar
    0.51
     нека
    0.50
    the
    0.49
    IUS
    0.49
    authorized
    0.46
    ALAR
    0.46
    onz
    0.45
    POSITIVE LOGITS
     enhancements
    0.49
     regressions
    0.48
     excitement
    0.47
     gjennom
    0.47
     Convert
    0.46
     setups
    0.46
     detonations
    0.45
     supernovae
    0.44
     converters
    0.43
     rotations
    0.43
    Act Density 0.000%

    No Known Activations