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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of inevitability or failing to achieve something

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

    absence of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.45
     emballage
    -0.40
    xmlhttp
    -0.39
     veau
    -0.38
    rawDesc
    -0.38
    writeFieldEnd
    -0.37
    šanai
    -0.37
     recuer
    -0.36
    édié
    -0.36
     Wohnen
    -0.36
    POSITIVE LOGITS
    Personensuche
    0.65
     surla
    0.63
    EndInit
    0.54
    íncia
    0.50
    CppMethod
    0.50
     JpaRepository
    0.49
    allible
    0.49
     MainAxisSize
    0.49
    jména
    0.46
    Guaranteed
    0.44
    Act Density 0.007%

    No Known Activations