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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meu
    -0.08
     handc
    -0.07
     رئيس
    -0.06
     Psych
    -0.06
    บน
    -0.06
     prz
    -0.06
    .subtract
    -0.06
    =yes
    -0.06
     predictive
    -0.06
     полит
    -0.06
    POSITIVE LOGITS
    While
    0.07
     Formatting
    0.06
     Пос
    0.06
    _SELF
    0.06
     [])
    0.06
     Desire
    0.06
    Instead
    0.06
     declares
    0.06
    素
    0.06
     Operational
    0.06
    Act Density 0.020%

    No Known Activations