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

    Neuronpedia

    INDEX
    Explanations

    list or comma separated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ıc
    0.28
    Iniciar
    0.26
    ་
    0.24
     абстра
    0.24
     آہستہ
    0.23
    த்தர
    0.23
    㻴
    0.23
    Begriffsklär
    0.23
    름
    0.23
    こんばんは
    0.23
    POSITIVE LOGITS
     that
    0.36
     when
    0.32
     When
    0.31
     kayak
    0.30
     these
    0.30
     the
    0.29
     if
    0.29
     বিশেষ
    0.28
     leveraging
    0.28
     shocked
    0.27
    Act Density 0.203%

    No Known Activations