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

    Neuronpedia

    INDEX
    Explanations

    people in different contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    مر
    -0.07
     directs
    -0.07
    weetalert
    -0.06
    콱
    -0.06
     nuevas
    -0.06
    .Button
    -0.06
     damaged
    -0.06
     Additionally
    -0.06
    .Buttons
    -0.06
    go
    -0.06
    POSITIVE LOGITS
    爱吃
    0.08
     epoch
    0.08
    औ
    0.07
     sci
    0.07
     overthrow
    0.07
    等于
    0.07
    CORE
    0.07
    Atomic
    0.07
     ard
    0.07
     mutation
    0.07
    Act Density 0.325%

    No Known Activations