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

    Neuronpedia

    INDEX
    Explanations

    references to monuments and similar structures

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

    erected monuments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sys
    -0.53
     Riau
    -0.47
    starts
    -0.44
    Dri
    -0.44
    Scooby
    -0.43
     agrico
    -0.43
     Roxy
    -0.43
    vedra
    -0.42
     Australie
    -0.42
    Flow
    -0.41
    POSITIVE LOGITS
     monument
    2.11
     Monument
    2.08
     monuments
    1.98
    Monument
    1.95
    monument
    1.84
     Monuments
    1.63
     monumento
    1.48
     monumentos
    1.41
     monumental
    0.99
     памят
    0.94
    Act Density 0.002%

    No Known Activations