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

    Neuronpedia

    INDEX
    Explanations

    instances of backslashes and their usage within mathematical notation or expressions

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

    mathematical and scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chriftian
    -0.62
     ſtate
    -0.59
     eſſ
    -0.55
     tranſ
    -0.54
     leaſt
    -0.53
     Diſ
    -0.53
     updateTime
    -0.52
    arraycopy
    -0.52
     itſelf
    -0.52
    luci
    -0.52
    POSITIVE LOGITS
    НИК
    0.51
    giày
    0.47
     |\
    0.45
    ፩
    0.44
     &\
    0.43
    tênis
    0.43
    "\
    0.41
    fortawesome
    0.41
     laiko
    0.40
     =\
    0.39
    Act Density 0.205%

    No Known Activations