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

    Neuronpedia

    INDEX
    Explanations

    annotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‐'
    -0.08
     MID
    -0.07
     Oriental
    -0.07
    알
    -0.07
     @{
    -0.06
     irres
    -0.06
     arrogant
    -0.06
     Alec
    -0.06
     поход
    -0.06
     pozdě
    -0.06
    POSITIVE LOGITS
    )*/↵
    0.07
     certainly
    0.06
    created
    0.06
     stanov
    0.06
    ErrorCode
    0.06
    ERP
    0.06
     ")
↵
    0.06
    changes
    0.06
     officially
    0.06
    ção
    0.06
    Act Density 0.000%

    No Known Activations