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

    Neuronpedia

    INDEX
    Explanations

    prefix + suffix compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     =
    0.98
    =\
    0.92
    =
    0.89
    ="
    0.88
    =""
    0.84
     +=
    0.84
    =-
    0.79
    (=
    0.78
    }=\
    0.77
    mult
    0.77
    POSITIVE LOGITS
     Grunge
    1.34
     Revenge
    1.25
     Collage
    1.21
     Refuge
    1.20
     Retro
    1.20
     Gameplay
    1.18
     Vintage
    1.17
     Outreach
    1.17
     Retreat
    1.16
     Wellbeing
    1.14
    Act Density 0.142%

    No Known Activations