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

    Neuronpedia

    INDEX
    Explanations

    concepts followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     different
    0.88
    不同的
    0.84
     Different
    0.84
     Elements
    0.81
     Reasons
    0.81
     diferentes
    0.81
     Theories
    0.79
     Rules
    0.76
    Different
    0.75
     عوامل
    0.74
    POSITIVE LOGITS
     powerhouse
    1.01
    based
    0.88
     orientated
    0.88
     extravaganza
    0.87
     oriented
    0.84
    oriented
    0.84
    aced
    0.79
     headquartered
    0.79
     அடிப்ப
    0.79
    -/
    0.79
    Act Density 1.234%

    No Known Activations