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

    Neuronpedia

    INDEX
    Explanations

    terms and policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ask
    0.80
     asking
    0.78
     спраши
    0.72
     asks
    0.71
     asked
    0.69
     Ask
    0.69
    ASK
    0.69
     ASK
    0.69
     Asking
    0.67
    ถาม
    0.65
    POSITIVE LOGITS
    Ace
    0.68
     Ace
    0.68
     ace
    0.66
     millions
    0.58
     ACE
    0.55
    ACE
    0.53
    Upload
    0.52
    Millions
    0.52
     създа
    0.51
    ace
    0.50
    Act Density 0.000%

    No Known Activations