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

    Neuronpedia

    INDEX
    Explanations

    software versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capo
    0.52
     cara
    0.52
     Boolean
    0.51
     encompass
    0.51
     Klasse
    0.50
     grove
    0.49
     over
    0.49
    ографи
    0.49
     fifty
    0.49
    コの
    0.48
    POSITIVE LOGITS
    版本
    0.80
    កំណ
    0.72
    version
    0.71
     版本
    0.71
     버전
    0.70
    Version
    0.69
    Ubuntu
    0.69
    ubuntu
    0.67
    バージョン
    0.67
    版本的
    0.65
    Act Density 0.070%

    No Known Activations