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

    Neuronpedia

    INDEX
    Explanations

    email greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desirous
    0.41
     filtrate
    0.41
     aconte
    0.37
     putchar
    0.36
     hedon
    0.35
     atribut
    0.35
     rosas
    0.35
     эпоху
    0.35
     rites
    0.34
     leaflets
    0.34
    POSITIVE LOGITS
    email
    0.45
    Email
    0.44
    EMAIL
    0.44
     email
    0.43
     EMAIL
    0.41
    ...@
    0.40
    mailto
    0.39
     Email
    0.39
     emailing
    0.38
     NDR
    0.38
    Act Density 0.051%

    No Known Activations