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

    Neuronpedia

    INDEX
    Explanations

    phrases that express comparisons or evaluations of quality

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

    specific common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    -0.54
    writeFieldEnd
    -0.51
    SequentialGroup
    -0.50
    wapV
    -0.48
     BrowserModule
    -0.48
    IUrlHelper
    -0.46
     насељу
    -0.45
    bagno
    -0.45
     acaso
    -0.44
    getSystemService
    -0.44
    POSITIVE LOGITS
    Bra
    0.40
    Pink
    0.40
     Pink
    0.39
     Horizontal
    0.38
    WireFormat
    0.37
     Hole
    0.37
     Ob
    0.36
    得
    0.36
     bra
    0.35
     bit
    0.35
    Act Density 0.155%

    No Known Activations