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

    Neuronpedia

    INDEX
    Explanations

    relationships involving the preposition "for" in various contexts

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

    Follows the word "pour" or "para"

    np_acts-logits-general · gemini-2.0-flash

    pour or para

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -1.07
     Majefty
    -1.06
    StructEnd
    -1.05
    NameInMap
    -1.05
     pleaſure
    -1.05
     Monfieur
    -1.02
     Jefus
    -1.01
    PerformLayout
    -0.97
     itſelf
    -0.95
     Efq
    -0.95
    POSITIVE LOGITS
     них
    0.69
     nich
    0.55
     un
    0.52
     
    0.50
     ello
    0.50
     el
    0.47
    poch
    0.46
    τί
    0.45
     una
    0.45
     "
    0.45
    Act Density 0.021%

    No Known Activations