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

    Neuronpedia

    INDEX
    Explanations

    HTTP bad responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     მე
    0.45
    sendMessage
    0.44
     PrintWriter
    0.42
    alignParentRight
    0.42
     Providing
    0.41
     Send
    0.41
    ometown
    0.40
    ToSend
    0.40
    normally
    0.40
    currentToken
    0.40
    POSITIVE LOGITS
     MM
    0.43
     dug
    0.40
     connexion
    0.40
    Plan
    0.40
     arose
    0.39
    itz
    0.38
     gard
    0.37
    æn
    0.37
     pp
    0.36
     syst
    0.36
    Act Density 0.006%

    No Known Activations