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

    Neuronpedia

    INDEX
    Explanations

    positive descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tm
    0.35
     adverse
    0.34
     unfavourable
    0.34
     underweight
    0.34
     preponder
    0.33
     ANOVA
    0.33
     continuum
    0.32
     disproportion
    0.32
     cropping
    0.32
     averse
    0.32
    POSITIVE LOGITS
     dreamy
    0.92
     luscious
    0.91
     fun
    0.89
     glamorous
    0.88
     exhilarating
    0.87
     thrilling
    0.86
     exciting
    0.86
     diversión
    0.86
     deliciously
    0.84
     scrumptious
    0.84
    Act Density 0.034%

    No Known Activations