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

    Neuronpedia

    INDEX
    Explanations

    AI toolkits and engines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firms
    0.45
     giants
    0.40
     vendors
    0.39
     provas
    0.38
     SELL
    0.37
     billions
    0.36
     probes
    0.36
    algorithms
    0.36
    島の
    0.35
    ্যাং
    0.35
    POSITIVE LOGITS
     toolkit
    0.61
     toolbox
    0.58
     empowerment
    0.54
     productividad
    0.54
     Toolkit
    0.50
     Empowerment
    0.45
    ための
    0.43
    情报
    0.43
     optimization
    0.43
     ért
    0.43
    Act Density 0.046%

    No Known Activations