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

    Neuronpedia

    INDEX
    Explanations

    weather forecasts and expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invented
    0.99
     craftsman
    0.85
     immutable
    0.83
     embodiment
    0.83
     heuristic
    0.81
     phenotype
    0.81
     epistemology
    0.81
     専用
    0.79
     fabricant
    0.79
     pseudonym
    0.78
    POSITIVE LOGITS
     midweek
    1.22
    idespread
    1.11
    引き続き
    1.07
     scattered
    1.06
     दोपहर
    1.05
    亮点
    1.04
     районов
    1.03
     अलर्ट
    1.03
     снижение
    1.02
    预计
    1.01
    Act Density 0.211%

    No Known Activations