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

    Neuronpedia

    INDEX
    Explanations

    categories or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Consequently
    0.45
    Consequently
    0.42
    ವೇಂದ್ರ
    0.38
     cardia
    0.37
    ದಾರ
    0.36
     Во
    0.36
     불구하고
    0.35
     RNN
    0.34
     首先
    0.34
     প্ৰ
    0.34
    POSITIVE LOGITS
     corresponds
    0.79
     είναι
    0.76
     isn
    0.75
     happened
    0.75
     wasn
    0.72
     involves
    0.71
     occurs
    0.70
    是
    0.68
     relates
    0.67
     precedes
    0.67
    Act Density 0.039%

    No Known Activations