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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or equations in LaTeX format

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

    mathematical symbols in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.57
    <tr>
    -0.53
    \/
    -0.49
     Bo
    -0.45
    ebx
    -0.44
    /
    -0.42
     also
    -0.42
     Gre
    -0.41
     CFP
    -0.41
     Green
    -0.41
    POSITIVE LOGITS
     $(\
    0.97
     $+\
    0.85
     $=\
    0.83
     $[\
    0.82
     $+
    0.82
     $(\%)$
    0.81
     $=
    0.78
     $|\
    0.78
     $<
    0.78
     $(-
    0.78
    Act Density 0.078%

    No Known Activations