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

    Neuronpedia

    INDEX
    Explanations

    verbal cues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Melissa
    0.38
    Ẓ
    0.38
     Melissa
    0.38
    樎
    0.37
     Phang
    0.36
    ityanath
    0.36
     Phillips
    0.36
    enye
    0.35
    桻
    0.35
    朓
    0.35
    POSITIVE LOGITS
     drawers
    0.41
     eternal
    0.40
     excitement
    0.39
     mineralization
    0.38
     handles
    0.38
     hygiene
    0.38
     indign
    0.38
     Hygiene
    0.38
     judgment
    0.38
     hordes
    0.38
    Act Density 0.000%

    No Known Activations