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

    Neuronpedia

    INDEX
    Explanations

    Flex headaches learned mass professionalism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contingencies
    0.52
     externalities
    0.49
    存档备份
    0.47
     capacitors
    0.46
     contingency
    0.46
     diets
    0.45
     exchangers
    0.45
     acids
    0.45
     winnings
    0.44
     achievements
    0.44
    POSITIVE LOGITS
    User
    0.55
     ICON
    0.54
    2
    0.51
     Carrot
    0.48
     Ici
    0.47
    user
    0.46
    Social
    0.46
    RC
    0.46
     Peralta
    0.46
     Hogg
    0.46
    Act Density 0.037%

    No Known Activations