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

    Neuronpedia

    INDEX
    Explanations

    website addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NYSE
    0.33
     Minneapolis
    0.33
     theses
    0.31
     Schools
    0.31
     Auckland
    0.31
     i
    0.30
     grantees
    0.30
     Companies
    0.29
     ~
    0.29
     Mortgage
    0.29
    POSITIVE LOGITS
    L
    0.43
    R
    0.35
    $_
    0.33
    E
    0.32
    variable
    0.32
     άλλ
    0.32
    P
    0.32
    ing
    0.30
    rä
    0.30
    cantidad
    0.30
    Act Density 0.319%

    No Known Activations