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

    Neuronpedia

    INDEX
    Explanations

    examples or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arsine
    0.43
    ………….
    0.42
    PictureBox
    0.42
     باس
    0.41
     APIDC
    0.40
     Padukone
    0.39
    ………..
    0.38
     polymerized
    0.38
     pyridine
    0.37
    董事长
    0.37
    POSITIVE LOGITS
    Exp
    0.47
    exp
    0.43
     Ex
    0.42
    EXP
    0.41
     Child
    0.41
    Ex
    0.41
     Exp
    0.41
     EXP
    0.41
     Alex
    0.40
    吧
    0.39
    Act Density 0.002%

    No Known Activations