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

    Neuronpedia

    INDEX
    Explanations

    is a / can earn / to sum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ¶Į
    -0.10
     -*-č\n
    -0.08
    _codegen
    -0.08
    ltk
    -0.08
     à¸ĵ
    -0.08
    TEGER
    -0.08
    #aa
    -0.07
    ););\n
    -0.07
    uraa
    -0.07
    lland
    -0.07
    POSITIVE LOGITS
     prec
    0.09
     dele
    0.09
     put
    0.08
     only
    0.08
     written
    0.07
     go
    0.07
     wander
    0.07
     present
    0.07
    ï¼ģãĢį\n\n
    0.07
     get
    0.07
    Act Density 0.266%

    No Known Activations