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

    Neuronpedia

    INDEX
    Explanations

    increase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -less
    -0.07
     Garden
    -0.07
    added
    -0.07
    Images
    -0.07
    hled
    -0.06
    Network
    -0.06
     biệt
    -0.06
     Bunifu
    -0.06
    stitutions
    -0.06
     But
    -0.06
    POSITIVE LOGITS
     savun
    0.07
     increase
    0.07
     ')
↵
    0.07
     decrease
    0.07
     �
    0.07
    \"";↵
    0.07
     defensively
    0.07
    ickle
    0.07
     ->↵
    0.07
    相同
    0.06
    Act Density 0.041%

    No Known Activations