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

    Neuronpedia

    INDEX
    Explanations

    information security consultancy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    го
    0.82
     अधिक
    0.82
     Cars
    0.78
    ای
    0.76
    चानक
    0.75
    й
    0.75
    Cars
    0.74
     abra
    0.72
     carros
    0.72
    紳
    0.69
    POSITIVE LOGITS
    osseum
    0.93
    ustration
    0.84
    ógica
    0.84
    erful
    0.83
    cellaneous
    0.81
    зывает
    0.81
    uitary
    0.80
     BlueprintName
    0.80
    Gc
    0.80
    vadipine
    0.79
    Act Density 0.000%

    No Known Activations