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

    Neuronpedia

    INDEX
    Explanations

    code, math, or latex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \\[
    0.71
     denoted
    0.58
     น้อย
    0.56
    ,​
    0.56
     ​
    0.56
    ,~
    0.55
    .​
    0.55
    �
    0.55
     signifying
    0.55
     alongside
    0.55
    POSITIVE LOGITS
    operatorname
    1.23
    underline
    1.02
    mathrm
    1.00
    boldsymbol
    0.98
    |_{\
    0.97
    bmod
    0.96
    |^{\
    0.93
    rceil
    0.92
    pounds
    0.89
    |_{
    0.89
    Act Density 0.015%

    No Known Activations