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

    Neuronpedia

    INDEX
    Explanations

    however,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sodass
    0.25
     isotherms
    0.22
    𒁍
    0.20
     koriste
    0.20
     resolvers
    0.20
    Stepper
    0.20
     chargers
    0.19
     antihy
    0.19
     hypert
    0.19
     stabilizers
    0.19
    POSITIVE LOGITS
    ,
    0.44
    ،
    0.36
    ၊
    0.34
    、
    0.32
     ,
    0.30
    ik
    0.30
    с
    0.28
    jenigen
    0.27
    ',
    0.26
    swering
    0.26
    Act Density 0.461%

    No Known Activations