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

    Neuronpedia

    INDEX
    Explanations

    ugly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    âte
    -0.07
    ()">↵
    -0.07
     Resources
    -0.07
    minate
    -0.07
    UpInside
    -0.07
    .Inventory
    -0.07
    utters
    -0.07
     revenge
    -0.07
     данным
    -0.06
    .CurrentRow
    -0.06
    POSITIVE LOGITS
     penetration
    0.07
    特性
    0.07
    ########################
    0.06
    纵向
    0.06
    本科生
    0.06
    ón
    0.06
    lic
    0.06
     Usuario
    0.06
    щ
    0.06
    alk
    0.06
    Act Density 0.017%

    No Known Activations