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

    Neuronpedia

    INDEX
    Explanations

    trick question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polynomial
    0.23
     from
    0.22
     ("
    0.20
     =>
    0.20
    0.20
     atoms
    0.20
     damage
    0.19
     owl
    0.19
     graph
    0.19
     isotherm
    0.19
    POSITIVE LOGITS
    虽然
    0.37
    Although
    0.32
    Unfortunately
    0.31
    雖然
    0.29
    There
    0.29
     absolutamente
    0.28
    Honestly
    0.28
    Yes
    0.27
    Aunque
    0.27
     некоторые
    0.27
    Act Density 3.513%

    No Known Activations