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

    Neuronpedia

    INDEX
    Explanations

    symbols used for mathematical notation and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    triangleq
    -0.92
    bigoplus
    -0.87
    Longrightarrow
    -0.83
    sqcup
    -0.74
     Curtis
    -0.73
    Gue
    -0.73
    triangleright
    -0.72
    _^
    -0.72
    widetilde
    -0.72
     يتيمه
    -0.72
    POSITIVE LOGITS
     \
    1.31
    ;\
    1.05
    >\
    1.05
    !\
    1.00
     [\
    0.97
    ?\
    0.96
    -\
    0.94
    "\
    0.93
     />\
    0.93
    (\
    0.93
    Act Density 0.206%

    No Known Activations