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

    Neuronpedia

    INDEX
    Explanations

    Network scanning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deportivo
    -0.09
    .WRAP
    -0.08
     newid
    -0.08
    Approval
    -0.08
     бу
    -0.07
     prescriptions
    -0.07
    enef
    -0.07
     restorative
    -0.07
     turma
    -0.07
     ਵਿਕ
    -0.07
    POSITIVE LOGITS
     reveals
    0.12
     revealed
    0.12
     revealing
    0.11
     probing
    0.11
     выяс
    0.11
     reveal
    0.11
     탐
    0.10
     clue
    0.10
     Reve
    0.10
    探
    0.10
    Act Density 0.015%

    No Known Activations