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

    Neuronpedia

    INDEX
    Explanations

    various types of formatting symbols and coding structures

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

    abbreviations like RT, PHA, STK, PROTO, phone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.57
    IsMutable
    -0.55
    igshid
    -0.53
    хьтан
    -0.53
    -0.52
    AsUp
    -0.51
    tvguidetime
    -0.49
    ंदीखरीदारी
    -0.49
    MLLoader
    -0.48
    verwijspagina
    -0.45
    POSITIVE LOGITS
     truly
    0.40
     since
    0.39
     itself
    0.39
    RequestMapping
    0.38
    Res
    0.38
    Remo
    0.38
    Qu
    0.37
     Rare
    0.36
     Sp
    0.35
     sc
    0.35
    Act Density 0.046%

    No Known Activations