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

    Neuronpedia

    INDEX
    Explanations

    philosophy and finance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    优点
    0.51
    DICTION
    0.50
    ISATION
    0.47
    ച്ചത്
    0.47
     favourable
    0.46
    짊
    0.45
    acité
    0.44
    ጩ
    0.44
     टंकी
    0.43
     प्रवृत्ति
    0.43
    POSITIVE LOGITS
     \
    0.47
     breaking
    0.42
     […]
    0.40
     rebuilding
    0.38
     ме
    0.37
     [...]
    0.37
     либо
    0.37
    解
    0.36
     metodo
    0.36
     ឬ
    0.36
    Act Density 0.000%

    No Known Activations