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

    Neuronpedia

    INDEX
    Explanations

    URLs and technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")
    0.42
    Manager
    0.41
    )
    0.41
    ın
    0.40
    ')
    0.38
    "});
    0.37
    ),
    0.37
    ",
    0.36
    ");
    0.35
    Management
    0.35
    POSITIVE LOGITS
    そして
    0.40
     amerikanischen
    0.40
    雅黑
    0.37
     rodean
    0.36
     tentu
    0.35
     Corbyn
    0.35
     blancs
    0.35
    syair
    0.35
     blancas
    0.35
     ненави
    0.34
    Act Density 0.001%

    No Known Activations