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

    Neuronpedia

    INDEX
    Explanations

    not merely X but Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emoz
    0.48
     sucede
    0.45
    学び
    0.45
     raccont
    0.44
     croit
    0.44
     suced
    0.43
     koron
    0.43
    gypte
    0.42
    ,]
    0.41
     felicidade
    0.41
    POSITIVE LOGITS
     Worksheet
    0.53
     Inbox
    0.46
     worksheets
    0.46
    棪
    0.45
     whiteboard
    0.44
     worksheet
    0.43
    遄
    0.42
     crates
    0.41
     alphanumeric
    0.41
    作业
    0.41
    Act Density 0.002%

    No Known Activations