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

    Neuronpedia

    INDEX
    Explanations

    code length and size checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ama
    0.49
    angi
    0.48
    hel
    0.48
    ap
    0.47
    quinone
    0.46
    ion
    0.45
    la
    0.44
    ⁹
    0.43
    gar
    0.43
    her
    0.42
    POSITIVE LOGITS
     footh
    0.42
     suficientes
    0.41
    鐒
    0.40
     taxi
    0.40
     బ్రిటిష్
    0.39
     жовт
    0.37
    त्तीस
    0.37
     नाबालिग
    0.37
     bulletins
    0.36
    ichts
    0.36
    Act Density 0.067%

    No Known Activations