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

    Neuronpedia

    INDEX
    Explanations

    approach is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sulfates
    1.57
    elun
    1.48
     sulfides
    1.35
     causando
    1.34
    essi
    1.33
     updatedAt
    1.32
     causar
    1.30
    elde
    1.30
     filóso
    1.29
    itatis
    1.29
    POSITIVE LOGITS
     Mr
    2.40
    Mr
    2.13
     Ms
    1.76
     Mrs
    1.73
    Mrs
    1.67
     mr
    1.54
     Dr
    1.48
    Ms
    1.45
     impressive
    1.41
    Dr
    1.36
    Act Density 0.075%

    No Known Activations