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

    Neuronpedia

    INDEX
    Explanations

    natural language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     最后
    0.89
     Strong
    0.84
     crise
    0.82
    prueba
    0.81
     Brave
    0.80
     सिंगापुर
    0.78
    лари
    0.78
     uite
    0.77
     गांवों
    0.77
     região
    0.77
    POSITIVE LOGITS
    గానే
    0.82
    ies
    0.77
    而在
    0.75
    istic
    0.72
     occuring
    0.68
    한
    0.66
    occurring
    0.65
    est
    0.65
     occurring
    0.65
     tym
    0.64
    Act Density 0.084%

    No Known Activations