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

    Neuronpedia

    INDEX
    Explanations

    expressions related to assistance and support

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

    explaining usefulness or benefit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.83
     queſta
    -0.74
     indígen
    -0.71
    WithIOException
    -0.69
    ſelben
    -0.69
    ſicht
    -0.68
     समीक्षक
    -0.68
     geſch
    -0.68
     ſche
    -0.67
     Biôgrafia
    -0.67
    POSITIVE LOGITS
     helps
    0.37
     BoxDecoration
    0.36
     help
    0.34
     ayuda
    0.33
    SourceChecksum
    0.31
    stdc
    0.30
     sirve
    0.28
     ayude
    0.27
     помогает
    0.26
     зав
    0.25
    Act Density 0.142%

    No Known Activations