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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and markdown formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ERS
    0.46
    OLYBD
    0.43
    cony
    0.39
    RT
    0.39
    Dollars
    0.39
     seroton
    0.39
    OLO
    0.39
    Vx
    0.39
    LException
    0.39
    ^*\
    0.38
    POSITIVE LOGITS
    </h2>
    0.54
    <h2>
    0.52
    ↵
    0.51
    <h3>
    0.47
    કર્
    0.44
    これは
    0.41
    </h3>
    0.41
    ↵↵
    0.40
    <0xE3>
    0.38
         
    0.38
    Act Density 0.000%

    No Known Activations