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

    Neuronpedia

    INDEX
    Explanations

    multiple choice answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    although
    0.36
    Mac
    0.36
    setObjectName
    0.35
    ларда
    0.35
    Nina
    0.35
    lor
    0.35
    VERE
    0.35
    Accom
    0.34
    essentially
    0.34
    bial
    0.34
    POSITIVE LOGITS
     Invis
    0.42
     walang
    0.41
     none
    0.39
     foolish
    0.38
     Profits
    0.38
     retribution
    0.38
     раньше
    0.37
     None
    0.36
     arbitrarily
    0.36
     quelconque
    0.36
    Act Density 0.032%

    No Known Activations