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

    Neuronpedia

    INDEX
    Explanations

    phrases related to travel and enjoyable experiences

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

    Follows common verbs

    np_acts-logits-general · gemini-2.0-flash

    story going back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horrend
    -0.63
    apimachinery
    -0.61
     horrible
    -0.60
     grotes
    -0.57
     cunt
    -0.56
    MergeFrom
    -0.55
     énorm
    -0.55
    Fuck
    -0.55
    OCCURRED
    -0.54
    RegressionTest
    -0.54
    POSITIVE LOGITS
    rungsseite
    0.74
     sizzling
    0.65
     ostavi
    0.62
     virtuales
    0.58
    setCellValue
    0.58
     sparkle
    0.56
     spéciaux
    0.56
    ovy
    0.55
     splash
    0.54
     sweet
    0.54
    Act Density 0.320%

    No Known Activations