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

    Neuronpedia

    INDEX
    Explanations

    freelance services and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overestimate
    0.46
     computer
    0.44
     computers
    0.44
     variability
    0.44
     Nobel
    0.43
     appreciably
    0.43
     billions
    0.42
     effectiveness
    0.42
     counterv
    0.42
     competence
    0.41
    POSITIVE LOGITS
     freelance
    0.71
     Lifestyle
    0.66
     независи
    0.63
    独立
    0.61
     Freel
    0.61
     indipendente
    0.60
     Independent
    0.59
     (@
    0.59
     Branding
    0.59
     Artist
    0.58
    Act Density 0.010%

    No Known Activations