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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waist
    -0.07
    throp
    -0.07
    ruit
    -0.06
    (ad
    -0.06
     worst
    -0.06
    ability
    -0.06
     gan
    -0.06
     brands
    -0.06
    freeze
    -0.06
    orraine
    -0.06
    POSITIVE LOGITS
    VPN
    0.06
    .createParallelGroup
    0.06
    (Blueprint
    0.06
     biz
    0.06
     Biz
    0.06
     Počet
    0.06
    리
    0.06
    .Physics
    0.06
    >'↵
    0.06
     lãi
    0.06
    Act Density 0.001%

    No Known Activations