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

    Neuronpedia

    INDEX
    Explanations

    annotations and documentation in code

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

    creates an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.74
     unknownFields
    -0.64
    WithIOException
    -0.61
     Administrativna
    -0.59
    LookAnd
    -0.57
     ब्रेकडाउन
    -0.56
     Italijanski
    -0.56
    parsedMessage
    -0.56
    SBATCH
    -0.55
    CppCodeGen
    -0.55
    POSITIVE LOGITS
     indi
    0.35
     mys
    0.33
     ins
    0.33
     hist
    0.33
     fac
    0.33
    രാ
    0.32
     fak
    0.31
     histor
    0.31
     ses
    0.30
     tempor
    0.30
    Act Density 0.006%

    No Known Activations