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

    Neuronpedia

    INDEX
    Explanations

    references to specific types of Sabian beliefs or figures

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

    Code paths, filenames, and server paths

    np_acts-logits-general · gemini-2.0-flash

    sab words and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     famí
    -0.56
     Straf
    -0.54
     ew
    -0.51
     llamas
    -0.51
    racite
    -0.50
    ../
    -0.50
    popd
    -0.49
     gynnwys
    -0.48
    цима
    -0.48
    萎
    -0.47
    POSITIVE LOGITS
     Sab
    0.81
    Sab
    0.77
     SAB
    0.75
    })));
    0.67
    BeginInit
    0.66
     ſee
    0.66
    Sabato
    0.65
     CURLOPT
    0.64
    (!__
    0.64
     houſe
    0.63
    Act Density 0.108%

    No Known Activations