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

    Neuronpedia

    INDEX
    Explanations

    install or installing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evolution
    0.43
     optical
    0.43
    Replace
    0.41
     obsc
    0.39
     attachment
    0.39
     averaged
    0.39
     metadata
    0.39
     pedigree
    0.39
     behavioral
    0.38
     stitch
    0.38
    POSITIVE LOGITS
     installieren
    0.63
    インストール
    0.61
     설치
    0.59
     Installing
    0.56
    安裝
    0.55
     instalado
    0.55
    Installing
    0.54
    installation
    0.54
     ইনস্ট
    0.54
    instal
    0.53
    Act Density 0.453%

    No Known Activations