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

    Neuronpedia

    INDEX
    Explanations

    Steve Jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (_.
    0.38
    rega
    0.38
     धारा
    0.37
    怨
    0.37
     webpack
    0.37
    Dex
    0.37
    мога
    0.37
    storm
    0.36
    Stephen
    0.35
     экстра
    0.35
    POSITIVE LOGITS
     Jobs
    0.53
     Steve
    0.49
     Balmer
    0.49
     Vai
    0.48
     Prec
    0.44
     irá
    0.43
     hydrodynamic
    0.43
     Ordnance
    0.41
     busc
    0.41
    țiuni
    0.40
    Act Density 0.001%

    No Known Activations