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

    Neuronpedia

    INDEX
    Explanations

    talk to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fol
    0.38
     endorsed
    0.37
     Accuracy
    0.36
     buffered
    0.36
     বক্তব্যের
    0.36
     fol
    0.36
     Concern
    0.36
     Ln
    0.36
     decouple
    0.36
     là
    0.35
    POSITIVE LOGITS
     openly
    0.61
     smack
    0.58
    ative
    0.53
    ativeness
    0.52
     abiert
    0.51
     turkey
    0.50
     nonsense
    0.50
    ATIVE
    0.50
     Smack
    0.48
     shop
    0.47
    Act Density 0.023%

    No Known Activations