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

    Neuronpedia

    INDEX
    Explanations

    origins and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ética
    0.56
    ソッド
    0.54
    ąd
    0.52
    motivated
    0.48
    ástica
    0.48
    ásticos
    0.45
    ូ
    0.45
    Xiao
    0.44
    ราะห์
    0.44
    zedł
    0.44
    POSITIVE LOGITS
    )
    0.51
    yle
    0.48
     अंकों
    0.47
    Type
    0.46
     テ
    0.44
    </i>
    0.44
    Text
    0.44
     Text
    0.44
     Brawl
    0.43
    Browse
    0.42
    Act Density 0.000%

    No Known Activations