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

    Neuronpedia

    INDEX
    Explanations

    references to Android-related terms or structures

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

    brain section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ex
    -0.33
     Red
    -0.32
     Gal
    -0.31
     Cor
    -0.30
    BeginContext
    -0.29
    gu
    -0.28
    gen
    -0.28
     Rede
    -0.27
    Cor
    -0.27
    di
    -0.26
    POSITIVE LOGITS
     betweenstory
    0.91
    transQ
    0.80
     Geiſt
    0.77
     desmotivaciones
    0.76
     Waſſer
    0.75
     Geſch
    0.74
    majánló
    0.71
     beſch
    0.71
     Administrativna
    0.68
     indígen
    0.68
    Act Density 0.005%

    No Known Activations