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

    Neuronpedia

    INDEX
    Explanations

    I express personal states and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proactively
    0.47
    गेटिव
    0.46
     अगर
    0.45
    していきます
    0.44
     completamente
    0.44
     gets
    0.43
    နဲ့
    0.43
     synergy
    0.43
     거라고
    0.43
    basically
    0.43
    POSITIVE LOGITS
     shall
    0.68
     scarcely
    0.66
     dares
    0.63
     dare
    0.61
     tremble
    0.59
     speak
    0.58
     trembled
    0.56
     shan
    0.56
     assure
    0.55
     cannot
    0.52
    Act Density 0.020%

    No Known Activations