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

    Neuronpedia

    INDEX
    Explanations

    happiness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Creator
    -0.08
    family
    -0.08
     Ion
    -0.07
    海上
    -0.07
     crew
    -0.07
     serie
    -0.07
    arl
    -0.06
     IPv
    -0.06
     math
    -0.06
     marvel
    -0.06
    POSITIVE LOGITS
    뙈
    0.07
    埫
    0.07
    팎
    0.07
     Hóa
    0.07
     pornost
    0.07
    ��
    0.07
    .FormBorderStyle
    0.06
    魉
    0.06
    .Ent
    0.06
    .all
    0.06
    Act Density 0.017%

    No Known Activations