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

    Neuronpedia

    INDEX
    Explanations

    openness, publicly available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    গঠনিক
    0.35
    íticas
    0.35
     Lieben
    0.34
    തായ
    0.34
    geführt
    0.34
     colp
    0.34
     génération
    0.33
    ropath
    0.33
     Informed
    0.33
     lograr
    0.33
    POSITIVE LOGITS
     open
    1.46
    开放
    1.44
    開放
    1.40
    open
    1.34
     openness
    1.31
    公开
    1.23
     откры
    1.22
    公開
    1.21
     відкри
    1.21
     공개
    1.19
    Act Density 0.046%

    No Known Activations