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

    Neuronpedia

    INDEX
    Explanations

    availability, desire, desk, sky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.55
    ung
    0.50
    ing
    0.49
    inen
    0.45
    _
    0.45
    was
    0.44
    um
    0.43
    ll
    0.43
    ess
    0.41
    yl
    0.41
    POSITIVE LOGITS
     மேம்ப
    0.54
     Nahi
    0.50
     wildflowers
    0.47
     Australie
    0.47
    ChooseServer
    0.46
     chronique
    0.46
     drzew
    0.46
    WaitingTime
    0.46
     mouve
    0.45
     sentire
    0.45
    Act Density 0.007%

    No Known Activations