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

    Neuronpedia

    INDEX
    Explanations

    instances of the backslash character used in mathematical notation

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

    LaTeX end environments and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.74
     Bobo
    -0.69
    ondissement
    -0.68
    eridge
    -0.67
     Geiſt
    -0.65
    Salmo
    -0.65
    entiment
    -0.64
     つ折り
    -0.63
    inoza
    -0.63
     CRUZ
    -0.63
    POSITIVE LOGITS
    \
    0.81
    <bos>
    0.74
    }\
    0.62
     \
    0.60
    
    0.52
    </
    0.50
    )\
    0.49
    $\
    0.48
     enví
    0.44
     $\
    0.43
    Act Density 0.005%

    No Known Activations