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

    Neuronpedia

    INDEX
    Explanations

    went, gone, go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Santa
    0.42
    SPRAY
    0.42
    '&
    0.40
    ﻫ
    0.40
     grate
    0.39
     revitalize
    0.39
    EnumValue
    0.38
    PIC
    0.38
     millennials
    0.38
     Valdez
    0.38
    POSITIVE LOGITS
     W
    0.36
    िवेदी
    0.36
     マイ
    0.36
    ッサ
    0.35
     Eas
    0.35
    base
    0.35
     Letters
    0.34
     Pum
    0.34
    აზე
    0.34
    ням
    0.34
    Act Density 0.000%

    No Known Activations