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

    Neuronpedia

    INDEX
    Explanations

    also called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ний
    0.28
    㤓
    0.26
    蹂
    0.25
    仃
    0.25
    фе
    0.24
    剻
    0.24
    Imidazole
    0.24
     INTERVAL
    0.24
     intervalos
    0.24
    开始
    0.24
    POSITIVE LOGITS
     Ham
    0.28
     Hawaiian
    0.28
     Australian
    0.28
     Maritime
    0.28
     Williams
    0.27
     Fuel
    0.25
     boarded
    0.25
     Fire
    0.25
    ham
    0.25
     Electrical
    0.25
    Act Density 0.000%

    No Known Activations