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

    Neuronpedia

    INDEX
    Explanations

    making judgments, decisions, requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     making
    0.93
     Making
    0.81
    making
    0.78
    Making
    0.75
     maken
    0.74
     makes
    0.70
     membuat
    0.65
     made
    0.65
     MAKING
    0.64
     maakt
    0.64
    POSITIVE LOGITS
     happen
    0.59
     inroads
    0.50
     decisions
    0.49
     strides
    0.48
     headway
    0.46
     incisions
    0.44
    登记
    0.41
    assertions
    0.41
    揖
    0.41
    nections
    0.41
    Act Density 0.018%

    No Known Activations