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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

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

    Separators in lists of numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    delimiters and quoted items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    -0.56
     sa
    -0.55
     Bel
    -0.53
     co
    -0.53
    -
    -0.53
    BASEPATH
    -0.52
     sem
    -0.51
     Se
    -0.51
     pre
    -0.51
     par
    -0.49
    POSITIVE LOGITS
    etc
    1.25
     etc
    1.20
     Roskov
    1.13
     themſelves
    1.05
     myſelf
    1.04
     pleaſure
    1.03
     itſelf
    1.02
     '\\;'
    1.01
    DockStyle
    1.00
    IntoConstraints
    0.99
    Act Density 1.140%

    No Known Activations