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

    Neuronpedia

    INDEX
    Explanations

    he performed an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palatable
    0.58
     detrimental
    0.57
     akin
    0.54
     substantial
    0.54
     pertinentes
    0.52
     imperative
    0.52
     formidable
    0.52
     worthwhile
    0.51
     prejudicial
    0.51
     constituting
    0.51
    POSITIVE LOGITS
     didn
    1.24
     did
    1.14
     gave
    1.11
     took
    1.07
     went
    1.05
     didnt
    1.03
     smiled
    0.96
     began
    0.93
     chose
    0.92
     showed
    0.90
    Act Density 0.164%

    No Known Activations