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

    Neuronpedia

    INDEX
    Explanations

    air fryer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.70
    湡
    0.63
    i
    0.59
    DB
    0.59
    S
    0.59
     for
    0.56
     IRL
    0.56
    :
    0.56
     onsite
    0.55
    .
    0.55
    POSITIVE LOGITS
    та
    0.89
     که
    0.78
     कहा
    0.76
    았
    0.75
    ਾ
    0.70
     colaboradores
    0.69
    า
    0.69
     powied
    0.67
     Tất
    0.66
     ნახ
    0.66
    Act Density 0.001%

    No Known Activations