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

    Neuronpedia

    INDEX
    Explanations

    desired outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terminology
    0.65
    를
    0.65
    terminology
    0.63
     need
    0.63
     शकतात
    0.62
     blandit
    0.61
     risiko
    0.60
    を高
    0.60
     trenger
    0.60
     needs
    0.59
    POSITIVE LOGITS
     desired
    3.47
     expected
    3.33
    expected
    3.10
     requested
    3.07
     anticipated
    3.05
    desired
    3.04
     predicted
    3.00
     Expected
    2.92
     planned
    2.90
     promised
    2.87
    Act Density 0.494%

    No Known Activations