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

    Neuronpedia

    INDEX
    Explanations

    Self improvement and care

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quedan
    -0.09
    ทอด
    -0.08
     restrictions
    -0.08
     misuse
    -0.08
     추
    -0.07
     отмет
    -0.07
    restriction
    -0.07
     шт
    -0.07
    яются
    -0.07
    dow
    -0.07
    POSITIVE LOGITS
     conducive
    0.09
     brains
    0.09
     daardoor
    0.09
     cognit
    0.08
    ，更
    0.08
     optimale
    0.08
     calmer
    0.08
     créativité
    0.08
     criatividade
    0.08
    -Gr
    0.08
    Act Density 0.049%

    No Known Activations