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

    Neuronpedia

    INDEX
    Explanations

    C code safety and git commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumerate
    0.46
    sending
    0.46
    lini
    0.44
     authorize
    0.43
     authorise
    0.43
    $:
    0.42
    mime
    0.42
    lng
    0.42
     департа
    0.42
     :{
    0.41
    POSITIVE LOGITS
    사
    0.50
     is
    0.49
    驷
    0.49
    是最
    0.48
     Hels
    0.47
     tenere
    0.46
     kan
    0.46
     Tool
    0.46
     mulai
    0.45
     catcher
    0.45
    Act Density 0.002%

    No Known Activations