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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax, particularly string manipulations and regular expressions

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

    Code that uses the `split` function

    np_acts-logits-general · gemini-2.0-flash

    string splitting and joining operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    baum
    -0.50
    …
    -0.46
    za
    -0.46
    —
    -0.45
    ...
    -0.45
     cutters
    -0.44
     comment
    -0.44
     —
    -0.41
     conclu
    -0.41
     मु
    -0.40
    POSITIVE LOGITS
     Efq
    0.99
    IndentedString
    0.96
    +#+#
    0.90
    MLLoader
    0.85
     beginnetje
    0.85
    #+#
    0.82
     myſelf
    0.82
     Roskov
    0.81
     doubtnut
    0.80
    IUrlHelper
    0.80
    Act Density 0.120%

    No Known Activations