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

    Neuronpedia

    INDEX
    Explanations

    year 2024 dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.48
    在
    0.42
     bilhões
    0.39
    ។
    0.39
    pple
    0.38
    hos
    0.35
    ;.
    0.35
    bbb
    0.35
    q
    0.34
    ppp
    0.34
    POSITIVE LOGITS
     This
    0.40
    on
    0.39
     A
    0.37
     It
    0.37
     (
    0.36
    ಲ್ಲ
    0.36
     These
    0.35
     simulator
    0.34
     stallion
    0.34
     shaker
    0.34
    Act Density 0.012%

    No Known Activations