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

    Neuronpedia

    INDEX
    Explanations

    Personal experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    basis
    -0.07
    ใหญ
    -0.07
     Informationen
    -0.06
    college
    -0.06
     Hose
    -0.06
    Send
    -0.06
    nof
    -0.06
     улы
    -0.06
    нциклопед
    -0.06
     setShow
    -0.06
    POSITIVE LOGITS
     издел
    0.06
     minutes
    0.06
     Dyn
    0.06
     References
    0.06
     Lor
    0.06
    ign
    0.06
    IVED
    0.06
     �
    0.06
     Mozilla
    0.06
     Fully
    0.06
    Act Density 0.065%

    No Known Activations