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

    Neuronpedia

    INDEX
    Explanations

    references to Facebook accounts and associated processes

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

    Fragments of non-English words

    np_acts-logits-general · gemini-2.0-flash

    mixing results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.51
    AutoScaleMode
    -0.47
    RetentionPolicy
    -0.47
    XmlType
    -0.46
    delta
    -0.46
    Хьажоргаш
    -0.44
    tela
    -0.43
    zied
    -0.42
     resourceCulture
    -0.41
     defaultstate
    -0.41
    POSITIVE LOGITS
     itſelf
    0.67
    — 
    0.63
    gså
    0.62
    @[+][
    0.61
    ITHUB
    0.60
    DetailComponent
    0.60
    restes
    0.59
    InputTagHelper
    0.58
    zsef
    0.58
    发表于
    0.57
    Act Density 0.125%

    No Known Activations