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

    Neuronpedia

    INDEX
    Explanations

    role assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orbidity
    0.44
     hyperglycemia
    0.40
    唪
    0.39
    제목
    0.38
    ုံ
    0.38
     (#{
    0.37
    疟
    0.37
    Lx
    0.37
     ওষুধের
    0.37
     navigable
    0.37
    POSITIVE LOGITS
     roles
    0.71
     role
    0.69
    角色
    0.66
    roles
    0.66
     Role
    0.63
     Roles
    0.63
    Roles
    0.63
    role
    0.60
    Role
    0.59
     роль
    0.59
    Act Density 0.012%

    No Known Activations