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

    Neuronpedia

    INDEX
    Explanations

    symbols or indicators related to system statuses or outputs

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.62
     Савезне
    -0.57
    Personendaten
    -0.57
     '\\;'
    -0.56
    
    -0.55
     SqlCommand
    -0.51
    formik
    -0.51
    期刊论文
    -0.50
    AutoScaleMode
    -0.48
     nakalista
    -0.47
    POSITIVE LOGITS
     BrowserModule
    0.57
     noastre
    0.51
     noastră
    0.50
    AnimationsModule
    0.43
    ⓧ
    0.42
     NgModule
    0.41
     equivalent
    0.40
     nostru
    0.40
    lugin
    0.40
    GIVEREF
    0.40
    Act Density 0.000%

    No Known Activations