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

    Neuronpedia

    INDEX
    Explanations

    relative clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puck
    -0.07
    /qu
    -0.06
    ollower
    -0.06
     Cumhur
    -0.06
     También
    -0.06
     Ideally
    -0.06
     kiểm
    -0.05
     cá
    -0.05
     blackColor
    -0.05
    .ToArray
    -0.05
    POSITIVE LOGITS
    emple
    0.07
     which
    0.07
    ého
    0.07
    สถานท
    0.06
    arel
    0.06
     Miche
    0.06
    HAL
    0.06
     makeover
    0.06
    そんな
    0.06
    GB
    0.06
    Act Density 0.097%

    No Known Activations