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

    Neuronpedia

    INDEX
    Explanations

    instructions or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     herbal
    0.70
     dragonfly
    0.62
     SQLite
    0.59
     Magento
    0.58
     biomass
    0.57
     sinusoidal
    0.56
     jetty
    0.56
    CellStyle
    0.55
     compris
    0.55
     autophagy
    0.55
    POSITIVE LOGITS
     darüber
    0.73
    ânia
    0.66
    ország
    0.64
    ovým
    0.61
     posicao
    0.61
     envoyé
    0.60
     น่ะ
    0.60
     मियां
    0.59
     voulez
    0.59
     সাহ
    0.58
    Act Density 0.001%

    No Known Activations