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

    Neuronpedia

    INDEX
    Explanations

    preferences and protections related to various subjects

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

    preferable or protections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Koffer
    -0.42
     prácti
    -0.42
     Stirn
    -0.41
     correspondiente
    -0.41
     lámpara
    -0.41
     virgen
    -0.39
     eigene
    -0.38
     coroa
    -0.38
     artesanía
    -0.38
     Fotografía
    -0.38
    POSITIVE LOGITS
     Audubon
    0.62
     protections
    0.60
    
    0.59
     accommodations
    0.59
     geologic
    0.57
    Erreferentziak
    0.57
     estekak
    0.56
     LGBTQ
    0.55
     gynhyrchwyd
    0.55
    новништво
    0.54
    Act Density 0.008%

    No Known Activations