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

    Neuronpedia

    INDEX
    Explanations

    messages or communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arginine
    0.43
     biochemistry
    0.36
     acyl
    0.36
     bestand
    0.35
     getopt
    0.35
     proteine
    0.35
     oncology
    0.35
    proteins
    0.34
     hw
    0.33
    FDA
    0.33
    POSITIVE LOGITS
     message
    0.77
     messages
    0.76
    message
    0.70
     mensajes
    0.68
    メッセージ
    0.68
     messaggio
    0.67
     повідом
    0.66
     informative
    0.64
     indiquant
    0.64
     mensaje
    0.63
    Act Density 0.493%

    No Known Activations