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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -folder
    -0.06
    chart
    -0.06
    �
    -0.06
    INS
    -0.06
     DataService
    -0.06
     TIME
    -0.05
     Blond
    -0.05
     ghosts
    -0.05
    Manage
    -0.05
     Grammar
    -0.05
    POSITIVE LOGITS
     bardzo
    0.07
    /Search
    0.07
     अवध
    0.06
     ):↵
    0.06
    业务
    0.06
    ristol
    0.06
     just
    0.06
     Aj
    0.06
    されて
    0.06
     блю
    0.06
    Act Density 0.108%

    No Known Activations